Survey of Predictive Analytics in Fundraising

Fundraising analytics publications by decades


When computer science is making rapid advances, one may ask “what new knowledge can be gained by reviewing previous work?” Cataloging previous work offers many benefits: a) we can notice the gaps to build upon, b) we can sense the future direction of research, and c) we can learn what has worked and what hasn’t. In this paper, I hope to offer an extensive survey of analytics applied to nonprofit fundraising. Using this survey, I note patterns and trends, and present research ideas for future work. The paper has the following structure. First, a brief history of analytics. Then different analytics methods. Followed by a review of the literature in applied analytics in fundraising. A summary of this review and future direction.

Review of Analytics

It is easy to get distracted by the current hype of Artificial Intelligence (AI), but when looked carefully, we can see the meaningful methods and techniques to make sense of the available data and information. Statistical analyses involve collecting, analyzing, drawing conclusions from the available data (Diez, Barr, and Cetinkaya-Rundel 2012). The field of statistics isn’t new. As Fienberg (1992) wrote in his review of statistics article, the classic probability theory was formed in the early 1700s, but the inference methods and statistical models were formed much later in the 1890s.

Advances in statistical research and computational power led to the first hype cycle of AI in the 1960s (Liao, Chu, and Hsiao 2012). Later, data mining became popular as a means to uncover patterns of significance using modern algorithms. Researchers named it Knowledge Discovery in Databases (KDD): the complete process of finding useful insights (Fayyad, Piatetsky-Shapiro, and Smyth 1996). Machine learning, a computer scientist’s way of saying pattern detection, surged in the early 2000s and now AI is back to the future. From a practitioner’s perspective, the differences among these terms and fields are now insignificant, but researchers in those fields care about these differences (Mannila 1996). In the end, as Fayyad, Piatetsky-Shapiro, and Smyth (1996) commented, “The unifying goal [of these methods] is extracting high-level knowledge from low-level data in the context of large data sets.”

Although the latest developments in natural language processing (NLP), natural language generation (NLG), computer vision, and deep-learning help us with other tasks than solely discovering knowledge (Young et al. 2018), we will find that the literature for nonprofit fundraising is focused on KDD. This makes sense because fundraising goes up when the right people are asked for the right amount. But in the future, we will see broader applications of data science, helping us automate tasks and increase productivity.

Methods and Techniques in Analytics

Since the field of analytics is expansive, let’s review and categorize the common methods and techniques used in the field. I will use these categories while reviewing the research in nonprofit fundraising.

Descriptive Statistics

Descriptive statistics use standard formulas to calculate measures that reflect the data. Some of these measures include mean, median, standard deviation, frequency, proportions, and other exploratory analyses. These measures give us quick insights into the data. Often, these measures are supported by graphs, such as scatter plots, histograms, and box plots. Such graphs help us see the correlations and patterns in the data (NIST/SEMATECH 2013).


Linear regression or least square methods estimate predictions by minimizing the sum of the differences between the actual data points and predicted value. As long as the parameter estimates can be multiplied to a variable (or its function) and these product terms can be added to form a function, we can use a linear regression – even if the function itself isn’t a straight line (NIST/SEMATECH 2013). But when the parameters take a non-linear form, we can’t use linear regression and could use non-linear regression. When we estimate parameters to build a model for some data, this approach is called parametric. In contrast, in a non-parametric approach we estimate a function that follows the data closely (James et al. 2013).

Regression methods can be used both for quantitative prediction (i.e. gift amount) as well as for predicting class probabilities (i.e. yes or no). Many approaches extend or build upon regression methods. In this paper, I have categorized them under regression. Some of these methods include logistic regression, Linear Discriminant Analysis (LDA), Generalized Additive Models (GAMs), Generalized Linear Models (GLMs), Ridge regression, Tobit regression, and Probit regression.


Classification methods predict the dependent variable into the different values of the dependent variable, such as “Yes” or “No.” These values are called classes. Although regression methods work on classifications problems, machine learning “divide-and-conquer” and “covering” techniques such as decision trees and rules are better equipped to handle missing values and noisy data (Witten et al. 2016).


Clustering methods attempt to divide the data into n groups of similar data points. These methods are called unsupervised learning methods as they do not require a dependent variable. They work by finding center points for each of these groups and then mark all the data points close to these centers as part of these clusters (James et al. 2013, 385).

Ensemble Methods

There are two types of ensemble methods: a) comparison of many algorithms, and b) using predictions from many algorithms. The comparison of multiple algorithms helps analysts see which methods work well for their data sets. Comparison prevents the potential loss of prediction performance compared to the analyst’s preferred method. Predictions from multiple algorithms can outperform a single algorithm by using stacking methods or super learners (Polley and van der Laan 2010; Polley, Rose, and van der Laan 2011).

Polley, Rose, and van der Laan (2011) argue that super learners work well with real-life datasets because no single algorithm can accurately model the data, but combining different algorithms provide us better estimates. As James et al. (2013) note, “there is no free lunch in statistics: no one method dominates all others over all possible data sets.”

Literature Review

Previous Work

Lindahl and Conley (2002) reviewed research and put it into two categories: “Motivational Studies” and “Predicting Alumni Giving.” The first category consists of work that studies why people choose to give. The second category includes research that identifies and test factors that could predict a person’s choice to give.

More recently, Bekkers and Wiepking (2010) reviewed more than 500 articles and categorized these works into eight topical areas. While these reviews summarized methods of philanthropy, this paper focuses on the uses of analytical methods.


I followed the methods and frameworks used in two popular review articles: “Educational data mining: A survey and a data mining-based analysis of recent works” (Peña-Ayala 2014) and “Data mining techniques and applications–A decade review from 2000 to 2011” (Liao, Chu, and Hsiao 2012). Both papers used comprehensive methods to collect and review the published works in data mining. Like their approaches, I started with these broad search terms in Google Scholar:

("data mining" OR analytics OR "machine learning" OR "data science" OR
 clustering OR statistics OR predictive) AND 
 (nonprofit OR fundraising OR fund-raising OR non-profit OR charity OR 
 donation OR philanthropy)

I filtered the results from these searches and used Google Scholar’s citations feature to search for other papers that cited these works. Additionally, I used Publish or Perish software (Harzing 2007) to run searches in Scoups and Microsoft Academic search databases as seen in Figure @ref(fig:pubperscreen). In the next phase, I looked at other cited works within these results.

Publish or Perish Search Screen

After reading the results from this search, I decided whether to include the research as part of this review. The excluded work fell into these categories:

  • Unpublished work
  • Undergraduate thesis
  • News articles
  • Company white papers
  • Research without analytics

I ended up with 145 works. Table @ref(tab:publishedworkscats) shows how the works were published, and you can see that Ph.D. dissertations account for the second most publications.

Categories of Published Works
Category Published Works
Article 78
PhD Thesis 51
In Proceedings 5
Book 4
In Collection 3
Masters Thesis 2
Tech Report 2


This review and its findings are limited because of my omissions and subjective bias. I omitted any work that I could not find digitally. Although USC library’s catalog is extensive and web searches can find many publications, I missed the digitally unavailable research (fewer than five). My subjective bias towards what qualifies as a study for this review likely excluded some publications. Also, I may have made errors with the search keywords. Finally, operator error: it is likely that I unintentionally missed some research.

By Decades

The first publication in this field is probably O’Connor’s dissertation on characteristics of alumni donors from 1961 (O’Connor 1961). But you can see from Figure @ref(fig:decadeschart) that majority of the works were published between 2010 and 2019. Another noticeable trend, as seen in Figure @ref(fig:decadesfacetmethodplot), is the use of a wider set of techniques during the 2010-2019 period – though regression still leads the way.

Total Number of Published Works by Decades

Methods by Decades.Note: Although regression techniques are oft-used methods, ensemble methods are finding greater use.

Table @ref(tab:methodsdecadecount) shows the raw numbers of the various analytics methods used over time. You can see regression methods and descriptive statistics total more than 100 studies, followed by 10 ensemble studies. This suggests that researchers feel confident in the results from regression methods. Or, researchers from other fields, especially computer science, have not studied fundraising problems.

Trends of Methods Used by Decade
Analytics Method 1960-1969 1970-1979 1980-1989 1990-1999 2000-2009 2010-2019 Total
CHAID 0 0 0 1 1 0 2
Clustering 0 0 0 1 2 4 7
Descriptive Statistics 1 9 11 3 5 5 34
Ensemble 0 0 0 0 1 9 10
Lifetime Value 0 0 0 2 1 0 3
Machine Learning 0 0 0 0 1 0 1
Markov Chains 0 0 1 1 0 0 2
Neural Networks 0 0 0 1 0 0 1
Other 0 1 0 0 2 2 5
Regression 0 2 7 17 21 30 77
Social Media 0 0 0 0 0 1 1
Support Vector Machines 0 0 0 0 0 1 1
Survival Analysis 0 0 0 0 1 0 1
Total 1 12 19 26 35 52 145

Fundraising analytics publications by methods and decades

By Method


CHAID is a decision tree learner, which Liihe (1998) used to study database marketing at UNICEF. Denizard-Ramsamy and Medina-Borja (2008) predicted financial vulnerability in non-profit organizations using CHAID; this is a rare paper as most of the studies in this review focus on donor identification.


Segmentation via clustering has a good use case in fundraising for customized marketing as well as prospect identification. Various researchers have applied segmentation at university settings (Cermak, File, and Prince 1994; Blanc and Rucks 2009; Luperchio 2009; E. J. Durango-Cohen, Torres, and Durango-Cohen 2013; P. L. Durango-Cohen, Durango-Cohen, and Torres 2013; Zhang 2014; Durango-Cohen and Balasubramanian 2015).

Descriptive Statistics

Descriptive statistics include mean, percentage distribution, correlations, Chi-squared tests, and Analysis of Variance (ANOVA). Most of the research in this category studied the effects of alumni characteristics to predict giving (O’Connor 1961; Morris 1970; Caruthers 1973; Blumenfeld and Sartain 1974; McKee 1975; Gardner 1975; Sundel et al. 1978; Markoff 1978; McKinney 1978; Riecken and Yavas 1979; Anderson 1981; Smith and Beik 1982; Keller 1982; Korvas 1984; Nelson 1984; Chewning 1984; Dietz 1985; McNally 1985; Haddad 1986; Schlegelmilch and Tynan 1989; Oglesby 1991; Hunter, Jones, and Boger 1999; Bingham Jr, Quigley Jr, and Murray 2003; Wylie 2004; Gunsalus 2005; Newman 2011; Loveday 2012; Bruyn and Prokopec 2013; Johnson 2013; Miller 2013).

A few notable exceptions were:

  • Frederick (1984) studied football success with institutional giving.
  • Berger and Smith (1997) analyzed the effects of framing the direct mail appeals.
  • Quigley, Bingham, and Murray (2002) measured the effects of gift acknowledgments on giving.
  • Magson and Routley (2009) looked at planned giving fundraising.


Ensemble methods often include machine learning techniques, which are either combined to improve performance or used for comparison. Potharst, Kaymak, and Pijls (2002) used neural networks and CHAID to improve direct marketing outcomes. Chen (2010) used regression, neural network, and SVMs on the Direct Marketing Education Foundation (DMEF) data. Ye (2017) used Naive Bayes, Random Forest, and SVM to predict major donors and compared the results from these methods. Other works in this category included: E. J. Durango-Cohen (2013), Moon and Azizi (2013), Udenze (2014), Torres (2014), Chung and Lee (2015), Kakrala and Chakraborty (2015), and Rattanamethawong, Sinthupinyo, and Chandrachai (2018).

Lifetime Value

Commonly used in the for-profit/marketing world, lifetime value calculates the future total profit from a customer. This value is used for segmentation and acquisition strategies. Some researchers have built models to calculate this value for donors (Hunter and Hill 1998; Sargeant 1998; Aldrich 2000).

Machine Learning

Many of the studies in the ensemble category fall in the machine learning category also. There was one study that didn’t fit in the ensemble category: Weerts and Ronca (2009) used classification trees to predict alumni giving.

Markov Chains

Markov Chains use probabilities of prior events to predict the probability of next events, and such a chain continues. A donor’s lifetime giving can also be structured as a chain of events to predict future giving. Soukup (1983) and Toohill et al. (1997) used Markov chains to predict giving.

Neural Networks

Like the machine learning models that fall under ensemble methods, a few neural network applications were also part of that category. But a standalone implementation of neural networks can be found in Goodman and Plouff (1997).


I placed other publications in this category if I couldn’t classify them. These tend to be either overarching frameworks (Birkholz 2008; Nandeshwar and Devine 2018), descriptive works (Herzlinger 1977), or rarely applied techniques for fundraising (Hashemi et al. 2009).


Researchers in higher education have applied different flavors of regression techniques, and as mentioned in the earlier section, I am using the term regression liberally. Most of these studies are Ph.D. dissertations from education schools and colleges (Manzer 1974; Miracle 1977; Yavas, Riecken, and Parameswaran 1981; Beeler 1982; Rosenblatt, Cusson, and McGown 1986; House 1987; Grill 1988; Leslie and Ramey 1988; Shadoian 1989; Duronio and Loessin 1990; Boyle 1990; Lindahl and Winship 1992, 1994; Hueston 1992; Burgess-Getts 1992; Mosser 1993; Martin 1993; Okunade, Wunnava, and Walsh Jr 1994; Bruggink and Siddiqui 1995; Taylor and Martin 1995; Pearson 1996; Baade and Sundberg 1996; Okunade and Berl 1997; Schlegelmilch, Love, and Diamantopoulos 1997; Selig 1999; Duncan 1999; Greenlee and Trussel 2000; Hanson 2000; Belfield and Beney 2000; Key 2001; Cunningham and Cochi-Ficano 2002; Monks 2003; Bennett 2003, 2006; Hoyt 2004; Marr, Mullin, and Siegfried 2005; Gaier 2005; Tsao and Coll 2005; Sun, Hoffman, and Grady 2007; Diehl 2007; Bohannon 2007; Terry and Macy 2007; Meer and Rosen 2008, 2012; Lawley 2008; McDearmon and Shirley 2009; Holmes 2009; Shen and Tsai 2009; Thompson 2010; Dickert, Sagara, and Slovic 2010; Verhaert 2010; Oliveira, Croson, and Eckel 2011; Steinnes 2011; Baruch and Sang 2012; Ketter 2013; Lara and Johnson 2013; Truitt 2013; Tiger and Preston 2013; Rau 2014; Skari 2014; Morgan 2014; Lertputtarak and Supitchayangkool 2014; Ropp 2014; Walcott 2015; Rau and Erwin 2015; Pinion 2016; Park et al. 2016; Veludo-de-Oliveira et al. 2016; Lawrence, Kudyba, and Lawrence 2017; Brunette, Vo, and Watanabe 2017; Faisal 2017; Saraih et al. 2018; Day 2018; Christian 2018; Liu, Feng, and Ouyang 2018; Naccarato 2019; Lowe 2019).

Social Media

Vequist IV (2017) studied the use of various social media and giving to various nonprofit organizations. Campaign performance data and other meta-data were used to improve the decision making of the stakeholders and increase social media user donations.

Support Vector Machines

One study using SVM is notable because it dealt with the imbalanced (or unbalanced) classes that we typically observe in the donation data i.e. either the proportion of donor records in the data is low or few major donors exist in the data. Kim, Chae, and Olson (2012) used SVMs to build a response model on imbalanced datasets.

Survival Analysis

Although survival analysis is used in analyzing data for a failure event, such as death, Drye, Wetherill, and Pinnock (2001) used it to predict a donor’s status in her giving lifecycle.

Quality Assessment

While reviewing the breadth of the methods used for nonprofit fundraising is useful, more important is assessing the rigor, credibility, and relevancy of the predictions in these published works. Wen et al. (2012) used a 10-question framework to assess the quality of each work. I used a similar method. I answered questions given in Table @ref(tab:qaquestions) for each published work; the possible answers were Yes, No, or Somewhat with weights of 1, 0, and 0.5 respectively. All questions, except for Q4 and Q6, are from Wen et al. (2012). Of course, these questions are suitable only for those works in which the researchers made predictions or built predictive models. It is also unfair to assess older research when obtaining enough computing power was a challenge. Also, my subjective bias can skew the findings.

Prediction quality assessment questions
ID Question
Q1 Are the estimation methods well defined and deliberate?
Q2 Is the experiment applied on sufficient data sets?
Q3 Is the estimation accuracy measured and reported?
Q4 Are the estimates significantly better than the baseline?
Q5 Is the proposed estimation method compared with other methods?
Q6 Can the findings be applied widely?
Q7 Are the findings of study clearly stated and supported by reporting results?
Author Analytics Method
Shadoian (1989) Regression
Liihe (1998) CHAID
Greenlee and Trussel (2000) Regression
Potharst, Kaymak, and Pijls (2002) Ensemble
Chen (2010) Ensemble
Kim, Chae, and Olson (2012) Support Vector Machines
Moon and Azizi (2013) Ensemble
Chung and Lee (2015) Ensemble
Ye (2017) Ensemble
Liu, Feng, and Ouyang (2018) Regression

Summary of Literature

Most of the studies in this review focused on either predicting the likelihood of a person donating or predicting the giving level or amount. An exception was the Greenlee and Trussel (2000) study of the financial stability of institutions. As Brittingham and Pezzullo (1990, 39) wrote about the predictive studies in fundraising, “Most of the studies are dissertations, and most are based on a single institution, most often a university. The results … do not support strong conclusions.” What was true in the 1990s remains true today. As we saw in the earlier sections, dissertations lare the second-most studies in applied analytics for fundraising.

Many dissertations followed a similar pattern: select variables based on literature, study each variable for correlations and significance, include selected variables for an estimation model, reject or accept the null hypothesis, and then present final results.

There are some challenges with this approach.

  1. These studies are often limited to one institution; hence the results cannot be generalized.
  2. This type of research primarily becomes about the application of a statistical technique to the researcher’s dataset and doesn’t contribute to knowledge advancement, either through the application of newer and different predictive methods or towards a unified theory of giving.
  3. This type of framework can be templatized using a programming language.

While building local predictive models are useful for development offices, we need either groundbreaking research to significantly improve on the donor classification problem, or we need to find different fundraising problems to solve.

Many of these studies used the null hypothesis significance testing (NHST) to infer the answers to research questions. This is problematic for two reasons:

  1. As Trafimow (2014) declared in his editorial of the Basic and Applied Social Psychology journal, “The null hypothesis significance testing procedure has been shown to be logically invalid and to provide little information about the actual likelihood of either the null or experimental hypothesis.” Then next year, while banning the null hypothesis significance testing procedure from the journal, Trafimow and Marks (2015) said, “\(p < .05\) bar is too easy to pass and sometimes serves as an excuse for lower quality research.”

  2. As Gliner, Leech, and Morgan (2002) noted, “A common misuse of NHST is the implication that statistical significance means theoretical or practical significance.” In these surveyed studies, you can find examples of researchers interpreting statistically significant results mistaken for important findings.

While most researchers report on the overall accuracy of their prediction models, very few report on other evaluation measures, such as precision, recall, or specificity. Another challenge is the lack of comparison to baseline proportions. Since such measures or comparisons aren’t reported, it is hard to assess whether the new predictive models performed better than guessing.

For example, say our data had 5% donors and 95% non-donors. We built a predictive model that classified donors and non-donors. Let’s say that this model had an overall accuracy of 95%. Now, if were to evaluate the model only based on accuracy, we might be satisfied with its performance. But even if we guess every row as a non-donor, we achieve 95% accuracy.

Similarly, if the data has 45% donors and 55% non-donors, and the model had an overall accuracy of 50%, it did worse than the baseline. Even if the predictive models aren’t compared to other models, they should at least be compared with the baseline. As my colleagues and I reported in another paper, if the overall accuracy rate is close to the baseline, then the complex analysis can be replicated by a simple majority vote model (Nandeshwar, Menzies, and Nelson 2011).

One benefit of the research done over decades into the likelihood of a person’s donation is that we have a comprehensive list of attributes, attitudes, and values that could go into building new predictive models.

Opportunities and Future Direction

Today’s technological advancement offers fascinating paths to study various problems in fundraising. Here are some suggestions and ideas to build on our knowledge of applications of data science in nonprofit fundraising.

  • Establish the baseline. In classification or numeric prediction models, use a majority vote or the mean value to compare the results against. Witten et al. (2016) call this model is called ZeroR. Also, consider using a simple, single-rule classification model known as 1R or OneR. Holte (1993) calculated the results from this simple model on many datasets and compared them with an advanced decision tree model and found that 1R was only “a few percentage points less accurate.”
  • Use and report a wider set of evaluation metrics. As we saw earlier, reporting accuracy can be misleading. We can consider different evaluation measures shown in the equations below (Branco, Torgo, and Ribeiro 2016). For example, Rau (2014, 30) reported that “76.4% of cases are correctly classified,” but you can see in Table @ref(tab:raustudycf) that 73% of their study data contained non-donors, so simply predicting everyone a non-donor, our accuracy is 73%. The study predicted only 88 donors who were actual donors, making the recall or true positive rate of 20%. Thus, the model failed at correctly identifying donors. Similarly, the F-measure and balanced accuracy were low at 0.32 and 59%.
Confusion Matrix for a Two-class Problem
Donor Non-donor
Actual Donor True Positive (TP) False Negative (FN)
Non-donor False Positive (FP) True Negative (TN)
Confusion Matrix from Rau (2014)
Donor Non-donor
Actual Donor 88 342
Non-donor 32 1126

\[\begin{equation} \mathrm{Precision} = \frac{TP}{TP+FP} \end{equation}\] \[\begin{equation} \mathrm{Recall} = \frac{TP}{TP+FN} \end{equation}\] \[\begin{equation} \mathrm{Specificity} = \frac{TN}{TN+FP} \end{equation}\] \[\begin{equation} \mathrm{F-measure} = 2\times\frac{Precision \times Recall}{Precision + Recall} \end{equation}\] \[\begin{equation} \mathrm{Balanced Accuracy } = \frac{Recall + Specificity}{2} \end{equation}\]

  • Consider selecting variables using feature subset selection (FSS). In his extensive study of feature subset selectors, Hall (1999) documented compared his feature (or variable) selector with other predictive techniques. He found that FSS removed redundant and irrelevant features, and in some cases, even improved the performance of the underlying predictive algorithms.
  • Consider class balancing methods. When the number of rows for one class (such as non-donor) is higher than the rows for any other class (such as donor), class imbalance occurs. To overcome this problem, Kim, Chae, and Olson (2012) used undersampling to reduce the number of majority class rows. Some other approaches to achieve class balance: oversampling the minority class rows, synthetic generation of minority class rows, such as SMOTE and family (Chawla et al. 2002; Han, Wang, and Mao 2005), and cost-sensitive learning (Domingos 1999).
  • Consider ensemble methods. Either combine various models (that is bagging, boosting, or stacking methods (see Witten et al. 2016, Section 8.1)) or compare various models and pre-processors. This type of comparison should be standard. Here’s pseudocode to explain this comparison:
For each dataset:
    Create P pre-processed datasets
    For each p in P:
        Divide p into ten cross-folds
        For each predictive learning technique t:
            Train t on 9-folds
            Test the model on the remaining folds
            Store results and the resulting model
  • Build a large database with data from diverse organizations. If researchers can collect data from many organizations, they can conduct a large-scale study to build predictive models. For example, Thompson (2010) used data from eight institutions. Such a large-scale study will show either that accurate donor classification is hard, or that a unified, single model can be built and we can research other topics. A related idea is what JOHNSON (1991) attempted: get anonymized data from the Internal Revenue Service (IRS) and build models on it.
  • Research other topics and approaches:
    • Consider modeling methods that work well with long-tail or skewed data, such as quantile regression (Perlich et al. 2007) or HyperSMURF, an ensemble method (Schubach et al. 2017).
    • Study creation of personalized appeals and communication. The latest Natural Language Processing and Generation (NLP and NLG) methods are far superior to previous methods (Yang et al. 2019), and they can be used to generate personalized appeals and communication. Ding and Pan (2016), for example, generated gain or risk framed text to increase the text’s appeal to the reader.
    • Study applications of graph theory to learn interests. Social graphs have value if all the connections in the graph can be known. A better use case for fundraising could be interest graphs, which identify the interests of people and connect people based on these interests (Yu et al. 2014).
    • Use NLG and NLP to automate tasks. Like creating personalized appeals, we can use pre-trained language models to summarize text, among other things, as shown by Liu and Lapata (2019). For example, using a simple Python text summarizer called sumy, I summarized an article on Bill Gates from
"In 1975, Gates and Allen formed Micro-Soft, a blend of "micro-computer" 
and "software" (they dropped the hyphen within a year). Bill Gates Fact 
Card Microsoft’s Software for IBM PCs As the computer industry grew, 
with companies like Apple, Intel and IBM developing hardware and 
components, Gates was continuously on the road touting the merits 
of Microsoft software applications. Since stepping down from Microsoft, 
Gates devotes much of his time and energy to the work of the Bill & 
Melinda Gates Foundation."


In this paper, I reviewed the literature of analytics for nonprofit fundraising. Although researchers have applied more sophisticated methods over time, regression methods remain the most-used technique for predicting a donor’s likelihood of giving and her giving amount. Also, dissertations account for second-most published works. Machine learning and ensemble techniques are increasingly in use, and we will see more research using these methods in the future. Researchers will also use natural language processing and generation, along with deep learning.

Quality assessment of publications in fundraising analytics

Searchable Bibliography of Analytics in Fundraising

O’Connor, William J. A Study Of Certain Factors Characteristic Of Alumni Who Provide Financial Support And Alumni Who Provide No Financial Support For Their College 1961 PHDTHESIS Descriptive Statistics 1960-1969
Morris, Donald A. A. An Analysis Of Donors Of $10,000 Or More To The $55 Million Program At The University Of Michigan 1970 PHDTHESIS Descriptive Statistics 1970-1979
Caruthers, Flora Ann Spencer Study of Certain Characteristics of Alumni Who Provide Financial Support and Alumni Who Provide No Financial Support for Their Alma Mater 1973 PHDTHESIS Descriptive Statistics 1970-1979
Manzer, Leslie Lee Charitable health organization donor behavior: an empirical study of value and attitude structure 1974 PHDTHESIS Regression 1970-1979
Warren S. Blumenfeld, Patricia L. Sartain Predicting alumni financial donation. 1974 Journal of Applied Psychology ARTICLE Descriptive Statistics 1970-1979 10.1037/h0037298
McKee, Dale F. An Analysis Of Factors Which Affect Alumni Participation And Support 1975 PHDTHESIS Descriptive Statistics 1970-1979
Herzlinger, Regina Why Data Systems in Nonprofit Organizations Fail. 1977 Harvard Business Review ARTICLE Other 1970-1979
Miracle, William D. Differences Between Givers And Nongivers To The University Of Georgia Annual Fund 1977 PHDTHESIS Regression 1970-1979
Markoff, Richard M. An Analysis Of The Relationship Of Alumni Giving And Level Of Participation In Voluntary Organizations: A Case Study 1978 PHDTHESIS Descriptive Statistics 1970-1979
McKinney, Ricardo J. Factors Among Select Donors And Nondonors Related To Major Gifts To A Private University 1978 PHDTHESIS Descriptive Statistics 1970-1979
Sundel, Harvey H, Zelman, William N, Weaver, Charles N, Pasternak, Richard E Fund raising: understanding donor motivation 1978 Social Work ARTICLE Descriptive Statistics 1970-1979
Glen Riecken, Ugur Yavas Meeting the Solicitation Challenge Through Marketing 1979 Administration in Social Work ARTICLE Descriptive Statistics 1970-1979 10.1300/j147v03n03_06
Anderson, Gerald L. Self-Esteem And Altruism Perceived As Motivational Factors For Alumni Giving, And Their Relationships To Various Donor Characteristics 1981 PHDTHESIS Descriptive Statistics 1980-1989
Ugur Yavas, Glen Riecken, Ravi Parameswaran Personality, organization-specific attitude, and socioeconomic correlates of charity giving behavior 1981 Journal of the Academy of Marketing Science ARTICLE Regression 1980-1989 10.1007/bf02723565
Keller,Mary J. C. An Analysis Of Alumni Donor And Non-Donor Characteristics At The University Of Montevallo (Alabama) 1982 PHDTHESIS Descriptive Statistics 1980-1989
Scott M. Smith, Leland L. Beik Market segmentation for fund raisers 1982 Journal of the Academy of Marketing Science ARTICLE Descriptive Statistics 1980-1989 10.1007/bf02729963
David J. Soukup A Markov Analysis of Fund-Raising Alternatives 1983 Journal of Marketing Research ARTICLE Markov Chains 1980-1989 10.1177/002224378302000310
Chewning, Paul B. The Attitudes Of Alumni Non-Donors, Donors, And Consecutive Donors Toward Drake University 1984 PHDTHESIS Descriptive Statistics 1980-1989
Frederick, Robert E. Intercollegiate Football Success And Institutional Private Support: A National Study Of 81 Public Universities, 1965-1979 1984 PHDTHESIS Descriptive Statistics 1980-1989
Korvas,Ronald J. The Relationship Of Selected Alumni Characteristics And Attitudes To Alumni Financial Support At A Private College 1984 PHDTHESIS Descriptive Statistics 1980-1989
Dietz, Larry H Iowa State University alumni contributions: an analysis of alumni giving patterns by selected class years, 1974 and 1979 1985 PHDTHESIS Descriptive Statistics 1980-1989
Haddad,Freddie D., Jr. An Analysis Of The Characteristics Of Alumni Donors And Non-Donors At Butler University 1986 PHDTHESIS Descriptive Statistics 1980-1989
Rosenblatt, Jerry A, Cusson, Alain J, McGown, Lee A model to explain charitable donation-health care consumer behavior 1986 Advances in Consumer Research ARTICLE Regression 1980-1989
House,Michael L. Annual fund raising in public higher education: The development and validation of a prediction equation 1987 ProQuest Dissertations and Theses PHDTHESIS Regression 1980-1989
Grill,Alan J. An analysis of the relationships of selected variables to financial support provided by alumni of a public university 1988 PHDTHESIS Regression 1980-1989
Leslie, Larry L, Ramey, Garey Donor behavior and voluntary support for higher education institutions 1988 The Journal of Higher Education ARTICLE Regression 1980-1989
Schlegelmilch, Bodo B, Tynan, AC The scope for market segmentation within the charity market: An empirical analysis 1989 Managerial and Decision Economics ARTICLE Descriptive Statistics 1980-1989
Shadoian,Holly L. A study of predictors of alumni philanthropy in public colleges 1989 PHDTHESIS Regression 1980-1989
Boyle,James J. College quality and alumni giving 1990 PHDTHESIS Regression 1990-1999
Margaret A. Duronio, Bruce A. Loessin Fund-Raising Outcomes and Institutional Characteristics in Ten Types of Higher Education Institutions 1990 The Review of Higher Education ARTICLE Regression 1990-1999 10.1353/rhe.1990.0013
Oglesby,Rodney A. Age, student involvement, and other characteristics of alumni donors and alumni non-donors of Southwest Baptist University 1991 PHDTHESIS Descriptive Statistics 1990-1999
Burgess-Getts,Linda Alumni as givers: An analysis of donor-nondonor behavior at a Comprehensive I institution 1992 PHDTHESIS Regression 1990-1999
Hueston,Frederick R. Predicting Alumni Giving: A Donor Analysis Test 1992 Fund raising management ARTICLE Regression 1990-1999
Wesley E Lindahl, Christopher Winship Predictive models for annual fundraising and major gift fundraising 1992 Nonprofit Management and Leadership ARTICLE Regression 1990-1999
Martin,Joseph C., Jr. Characteristics of alumni donors and non-donors at a Research I, public university 1993 PHDTHESIS Regression 1990-1999
Mosser, John Wayne Predicting Alumni/ae Gift Giving Behavior: A Structural Equation Model Approach 1993 PHDTHESIS Regression 1990-1999
Dianne S.P. Cermak, Karen Maru File, Russ Alan Prince A benefit segmentation of the major donor market 1994 Journal of Business Research ARTICLE Clustering 1990-1999 10.1016/0148-2963(94)90016-7
Okunade, Albert Ade, Wunnava, Phanindra V, Walsh Jr, Raymond Charitable giving of alumni: micro-data evidence from a large public university 1994 American Journal of Economics and Sociology ARTICLE Regression 1990-1999
Wesley E Lindahl, Christopher Winship A logit model with interactions for predicting major gift donors 1994 Research in Higher Education ARTICLE Regression 1990-1999 10.1007/bf02497084
Alton L. Taylor, Joseph C. Martin Characteristics of alumni donors and nondonors at a Research I, public university 1995 Research in Higher Education ARTICLE Regression 1990-1999 10.1007/bf02208312
Bruggink, Thomas H, Siddiqui, Kamran An econometric model of alumni giving: A case study for a liberal arts college 1995 The American Economist ARTICLE Regression 1990-1999
Pearson,William E. A study of donor predictability among graduates of a school of education within a Research I, public university 1996 PHDTHESIS Regression 1990-1999
Robert A. Baade, Jeffrey O. Sundberg What determines alumni generosity? 1996 Economics of Education Review ARTICLE Regression 1990-1999 10.1016/0272-7757(95)00026-7
Berger, Paul D, Smith, Gerald E The effect of direct mail framing strategies and segmentation variables on university fundraising performance 1997 Journal of Direct Marketing ARTICLE Descriptive Statistics 1990-1999
Goodman, Steve, Plouff, Gary Neural Network Modeling: Artificial Intelligence Marketing Hits the Non-Profit World 1997 Fund Raising Management ARTICLE Neural Networks 1990-1999
Jim Toohill, Lisa Mullins, Jean Barclay, Mike Sadnicki Turning data into donations: A predictive model for individual giving 1997 International Journal of Nonprofit and Voluntary Sector Marketing ARTICLE Markov Chains 1990-1999 10.1002/nvsm.6090020205
Okunade, Albert A, Berl, Robert L Determinants of charitable giving of business school alumni 1997 Research in higher education ARTICLE Regression 1990-1999
Schlegelmilch, Bodo B, Love, Alix, Diamantopoulos, Adamantios Responses to different charity appeals: the impact of donor characteristics on the amount of donations 1997 European Journal of Marketing ARTICLE Regression 1990-1999
Adrian Sargeant Donor lifetime value: An empirical analysis 1998 International Journal of Nonprofit and Voluntary Sector Marketing ARTICLE Lifetime Value 1990-1999 10.1002/nvsm.6090030403
Tim Hunter, Richard Hill Prediction of donor lifetime value and the development of true segmented donor strategy 1998 International Journal of Nonprofit and Voluntary Sector Marketing ARTICLE Lifetime Value 1990-1999 10.1002/nvsm.6090030405
von der Liihe, Markus How to get more donors: Unicef database marketing and data mining for non-commercial organizations 1998 WIT Transactions on Information and Communication Technologies ARTICLE CHAID 1990-1999
Brian Duncan Modeling charitable contributions of time and money 1999 Journal of Public Economics ARTICLE Regression 1990-1999 10.1016/s0047-2727(98)00097-8
Catrelia S. Hunter, Enid B. Jones, Charlotte Boger A Study of the Relationship between Alumni Giving and Selected Characteristics of Alumni Donors of Livingstone College, {NC 1999 Journal of Black Studies ARTICLE Descriptive Statistics 1990-1999 10.1177/002193479902900404
Selig,Camden W. A study of donor predictability among alumni athletes at the University of Virginia 1999 PHDTHESIS Regression 1990-1999
C.R. Belfield, A.P. Beney What Determines Alumni Generosity? Evidence for the {UK 2000 Education Economics ARTICLE Regression 2000-2009 10.1080/096452900110300
Hanson, Sheila Kay Alumni Characteristics that Predict Promoting and Donating to Alma Mater: Implications for Alumni Relations 2000 PHDTHESIS Regression 2000-2009
Janet S. Greenlee, John M. Trussel Predicting the Financial Vulnerability of Charitable Organizations 2000 Nonprofit Management and Leadership ARTICLE Regression 2000-2009 10.1002/nml.11205
Tobin M. Aldrich How much are new donors worth? Making donor recruitment investment decisions based on lifetime value analysis 2000 International Journal of Nonprofit and Voluntary Sector Marketing ARTICLE Lifetime Value 2000-2009 10.1002/nvsm.99
Jennifer Key Enhancing fundraising success with custom data modelling 2001 International Journal of Nonprofit and Voluntary Sector Marketing ARTICLE Regression 2000-2009 10.1002/nvsm.159
Tim Drye, Graham Wetherill, Alison Pinnock Donor survival analysis: an alternative perspective on lifecycle modelling 2001 International Journal of Nonprofit and Voluntary Sector Marketing ARTICLE Survival Analysis 2000-2009 10.1002/nvsm.158
Charles J. Quigley, Frank G. Bingham, Keith B. Murray An Analysis of the Impact of Acknowledgement Programs on Alumni Giving 2002 Journal of Marketing Theory and Practice ARTICLE Descriptive Statistics 2000-2009 10.1080/10696679.2002.11501921
Cunningham, Brendan M, Cochi-Ficano, Carlena K The determinants of donative revenue flows from alumni of higher education: An empirical inquiry 2002 Journal of Human resources ARTICLE Regression 2000-2009
Rob Potharst, Uzay Kaymak, Wim Pijls Neural Networks for Target Selection in Direct Marketing 2002 INCOLLECTION Ensemble 2000-2009 10.4018/978-1-930708-31-0.ch006
Bingham Jr, Frank G, Quigley Jr, Charles J, Murray, Keith B An investigation of the influence acknowledgement programs have on alumni giving behavior: Implications for marketing strategy 2003 Journal of Marketing for Higher Education ARTICLE Descriptive Statistics 2000-2009
Monks, James Patterns of giving to one’s alma mater among young graduates from selective institutions 2003 Economics of Education review ARTICLE Regression 2000-2009
Roger Bennett Factors underlying the inclination to donate to particular types of charity 2003 International Journal of Nonprofit and Voluntary Sector Marketing ARTICLE Regression 2000-2009 10.1002/nvsm.198
Hoyt, Jeff E Understanding alumni giving: Theory and predictors of donor status 2004 INPROCEEDINGS Regression 2000-2009
Wylie, Peter B Data mining for fund raisers: How to use simple statistics to find the gold in your donor database–even if you hate statistics: A starter guide 2004 BOOK Descriptive Statistics 2000-2009
Marr, Kelly A, Mullin, Charles H, Siegfried, John J Undergraduate financial aid and subsequent alumni giving behavior 2005 The Quarterly Review of Economics and Finance ARTICLE Regression 2000-2009
Robert Gunsalus The Relationship of Institutional Characteristics and Giving Participation Rates of Alumni 2005 International Journal of Educational Advancement ARTICLE Descriptive Statistics 2000-2009 10.1057/palgrave.ijea.2140214
Scott Gaier Alumni Satisfaction with Their Undergraduate Academic Experience and the Impact on Alumni Giving and Participation 2005 International Journal of Educational Advancement ARTICLE Regression 2000-2009 10.1057/palgrave.ijea.2140220
Tsao,James C., Coll,Gary To Give or Not to Give: Factors Determining Alumni Intent to Make Donations as a PR Outcome 2005 Journalism & Mass Communication Educator ARTICLE Regression 2000-2009
Roger Bennett Predicting the Lifetime Durations of Donors to Charities 2006 Journal of Nonprofit {&} Public Sector Marketing ARTICLE Regression 2000-2009 10.1300/j054v15n01_03
Bohannon, Tom Predictive modelling in higher education 2007 INPROCEEDINGS Regression 2000-2009
Diehl, Abigail G The relationship between alumni giving and receipt of institutional scholarships among undergraduate students at a public, land-grant institution 2007 PHDTHESIS Regression 2000-2009
Terry, Neil, Macy, Anne Determinants of alumni giving rates 2007 Journal of Economics and Economic Education Research ARTICLE Regression 2000-2009
Xiaogeng Sun, Sharon C Hoffman, Marilyn L Grady A multivariate causal model of alumni giving: Implications for alumni fundraisers 2007 International Journal of Educational Advancement ARTICLE Regression 2000-2009
Denizard-Ramsamy, Wilhelrm, Medina-Borja, Alexandra Using chaid as a method to predict financial vulnerablity in non-profit organizations 2008 INPROCEEDINGS CHAID 2000-2009
Jonathan Meer, Harvey Rosen The Impact of Athletic Performance on Alumni Giving: An Analysis of Micro Data 2008 TECHREPORT Regression 2000-2009 10.3386/w13937
Joshua Birkholz Fundraising analytics: Using data to guide strategy 2008 BOOK Other 2000-2009
Lawley,Cecelia D. Factors that affect alumni loyalty at a public university 2008 PHDTHESIS Regression 2000-2009
Anyuan Shen, Chih-Yang Tsai Are single-gift committed donors different from their multiple-gift counterparts? 2009 International Journal of Nonprofit and Voluntary Sector Marketing ARTICLE Regression 2000-2009 10.1002/nvsm.387
David J. Weerts, Justin M. Ronca Using classification trees to predict alumni giving for higher education 2009 Education Economics ARTICLE Machine Learning 2000-2009 10.1080/09645290801976985
Hashemi,Ray R., Le Blanc,Louis,A., Bahrami,Azita A., Bahar,Mahmood, Traywick,Bryan Association Analysis of Alumni Giving: A Formal Concept Analysis 2009 International Journal of Intelligent Information Technologies ARTICLE Other 2000-2009
J Travis McDearmon, Kathryn Shirley Characteristics and institutional factors related to young alumni donors and non-donors 2009 International Journal of Educational Advancement ARTICLE Regression 2000-2009 10.1057/ijea.2009.29
Jessica Holmes Prestige, charitable deductions and other determinants of alumni giving: Evidence from a highly selective liberal arts college 2009 Economics of Education Review ARTICLE Regression 2000-2009 10.1016/j.econedurev.2007.10.008
Louis A Le Blanc, Conway T Rucks Data mining of university philanthropic giving: Cluster-discriminant analysis and Pareto effects 2009 International Journal of Educational Advancement ARTICLE Clustering 2000-2009 10.1057/ijea.2009.28
Luperchio, Dan Data Mining and Predictive Modeling in Institutional Advancement: How Ten Schools Found Success. Technical Report. 2009 TECHREPORT Clustering 2000-2009
Nigel Magson, Claire Routley Using data in legacy fundraising: a practical approach 2009 International Journal of Nonprofit and Voluntary Sector Marketing ARTICLE Descriptive Statistics 2000-2009 10.1002/nvsm.374
Qin Chen Predictive modeling for non-profit fundraising 2010 MASTERSTHESIS Ensemble 2010-2019
Stephan Dickert, Namika Sagara, Paul Slovic Affective motivations to help others: A two-stage model of donation decisions 2010 Journal of Behavioral Decision Making ARTICLE Regression 2010-2019 10.1002/bdm.697
Thompson,Lori A. Data mining for higher education advancement: A study of eight North American colleges and universities 2010 PHDTHESIS Regression 2010-2019
Verhaert, Griet The Role of Database Marketing in Improving Direct Mail Fundraising 2010 PHDTHESIS Regression 2010-2019
Angela C.M. de Oliveira, Rachel T.A. Croson, Catherine Eckel The giving type: Identifying donors 2011 Journal of Public Economics ARTICLE Regression 2010-2019 10.1016/j.jpubeco.2010.11.012
Donald N. Steinnes An Econometric Analysis Of Aging And Alumni/ae Altruism 2011 International Business {&} Economics Research Journal ({IBER}) ARTICLE Regression 2010-2019 10.19030/iber.v1i5.3924
Melissa D Newman Does membership matter? Examining the relationship between alumni association membership and alumni giving 2011 International Journal of Educational Advancement ARTICLE Descriptive Statistics 2010-2019 10.1057/ijea.2011.5
Baruch, Yehuda, Sang, Katherine JC Predicting MBA graduates’ donation behaviour to their alma mater 2012 Journal of Management Development ARTICLE Regression 2010-2019 10.1108/02621711211253268
Gitae Kim, Bongsug Kevin Chae, David L. Olson A support vector machine ({SVM}) approach to imbalanced datasets of customer responses: comparison with other customer response models 2012 Service Business ARTICLE Support Vector Machines 2010-2019 10.1007/s11628-012-0147-9
Jonathan Meer, Harvey S. Rosen Does generosity beget generosity? Alumni giving and undergraduate financial aid 2012 Economics of Education Review ARTICLE Regression 2010-2019 10.1016/j.econedurev.2012.06.009
Loveday, Christine Hawk An analysis of the variables associated with alumni giving and employee giving to a mid-sized southeastern university 2012 PHDTHESIS Descriptive Statistics 2010-2019
Andrew Tiger, Landon Preston Logged In And Connected? A Quantitative Analysis Of Online Course Use And Alumni Giving 2013 American Journal of Business Education ({AJBE}) ARTICLE Regression 2010-2019 10.19030/ajbe.v6i3.7816
Arnaud De Bruyn, Sonja Prokopec Opening a donor’s wallet: The influence of appeal scales on likelihood and magnitude of donation 2013 Journal of Consumer Psychology ARTICLE Descriptive Statistics 2010-2019 10.1016/j.jcps.2013.03.004
Christen Lara, Daniel Johnson The anatomy of a likely donor: econometric evidence on philanthropy to higher education 2013 Education Economics ARTICLE Regression 2010-2019 10.1080/09645292.2013.766672
Durango-Cohen, Elizabeth J, Torres, Ram{‘o}n L, Durango-Cohen, Pablo L Donor segmentation: When summary statistics don’t tell the whole story 2013 Journal of Interactive Marketing ARTICLE Clustering 2010-2019
Elizabeth J Durango-Cohen Modeling contribution behavior in fundraising: Segmentation analysis for a public broadcasting station 2013 European Journal of Operational Research ARTICLE Ensemble 2010-2019 10.1016/j.ejor.2013.01.008
Johnson,Elizabeth A. M. Factors associated with non-traditional and traditional undergraduate alumni giving to alma maters 2013 PHDTHESIS Descriptive Statistics 2010-2019
Ketter, Jason W Predictors of Alumni Donor Behavior in Graduates of the Traditional MBA and iMBA Programs at The Pennsylvania State University 2013 PHDTHESIS Regression 2010-2019
Miller,Myra E. Why alumni give: How campus environment and sense of belonging shape nontraditional students’ intent to give financially to their university 2013 PHDTHESIS Descriptive Statistics 2010-2019
Pablo L. Durango-Cohen, Elizabeth J. Durango-Cohen, Ram{‘{o}}n L. Torres A Bernoulli{}Gaussian mixture model of donation likelihood and monetary value: An application to alumni segmentation in a university setting 2013 Computers {&} Industrial Engineering ARTICLE Clustering 2010-2019 10.1016/j.cie.2013.08.007
Sangkil Moon, Kathryn Azizi Finding Donors by Relationship Fundraising 2013 Journal of Interactive Marketing ARTICLE Ensemble 2010-2019 10.1016/j.intmar.2012.10.002
Truitt, Joshua The relationship between student engagement and recent alumni donors at Carnegie baccalaureate colleges located in the southeastern United States 2013 PHDTHESIS Regression 2010-2019
Kevin MacDonell, Peter Wylie Score! Data-Driven Success for Your Advancement Team 2014 BOOK Other 2010-2019
Lisa Ann Skari Community college alumni: Predicting who gives 2014 Community College Review ARTICLE Regression 2010-2019
Morgan, Robert Andrew Factors that lead Millennial alumni to donate to their alma mater 2014 PHDTHESIS Regression 2010-2019
Nicholas Rau Predictive Modeling of Alumni Donors: An Engagement Model for Fundraising in Postsecondary Education 2014 PHDTHESIS Regression 2010-2019
Ropp, Christopher Tylerr The relationship between student academic engagement and alumni giving at a public, state flagship university 2014 PHDTHESIS Regression 2010-2019
Sarunya Lertputtarak, Surat Supitchayangkool Factors Influencing Alumni Donations 2014 International Journal of Business and Management ARTICLE Regression 2010-2019 10.5539/ijbm.v9n3p170
Torres,Ramon L. Dynamic Segmentation Modeling: Application of Finite Mixture Models to Explain the Giving Behavior of Donors in a University Setting 2014 PHDTHESIS Ensemble 2010-2019
Udenze, Adrian APPLICATION OF DATA MINING TECHNIQUES TO PROBLEMS IN FUND RAISING 2014 International Journal of Current Research and Review ARTICLE Ensemble 2010-2019
Weizeng Zhang Segmentation modeling: Applications of Finite Mixture Regression Models in University Fundraising and Management of Transportation Infrastructure 2014 PHDTHESIS Clustering 2010-2019
Durango-Cohen, Elizabeth J, Balasubramanian, Siva K Effective segmentation of university alumni: Mining contribution data with finite-mixture models 2015 Research in Higher Education ARTICLE Clustering 2010-2019
Jinwook Chung, Kyumin Lee A Long-Term Study of a Crowdfunding Platform 2015 INPROCEEDINGS Ensemble 2010-2019 10.1145/2700171.2791045
Kakrala, Ramcharan, Chakraborty, Goutam Donor Sentiment and Characteristic Analysis Using SAS® Enterprise Miner™ and SAS® Sentiment Analysis Studio 2015 INPROCEEDINGS Ensemble 2010-2019 10.13140/RG.2.1.2716.7842
Mark E Walcott Predictive modeling and alumni fundraising in higher education 2015 PHDTHESIS Regression 2010-2019
Nicholas E Rau, T Dary Erwin Using student engagement to predict alumni donors: An analytical model 2015 The Journal of Nonprofit Education and Leadership ARTICLE Regression 2010-2019
Chanmin Park, Yong Jae Ko, Hee Youn Kim, Michael Sagas, Melfy Eddosary Donor motivation in college sport: Does contribution level matter? 2016 Social Behavior and Personality: an international journal ARTICLE Regression 2010-2019 10.2224/sbp.2016.44.6.1015
Pinion, Tyson L Factors That Influence Alumni Giving at Three Private Universities 2016 PHDTHESIS Regression 2010-2019
Tania M. Veludo-de-Oliveira, Ibrahim S. Alhaidari, Mirella Yani-de-Soriano, Shumaila Y. Yousafzai Comparing the Explanatory and Predictive Power of Intention-Based Theories of Personal Monetary Donation to Charitable Organizations 2016 VOLUNTAS}: International Journal of Voluntary and Nonprofit Organizations ARTICLE Regression 2010-2019 10.1007/s11266-016-9690-7
Brunette, Charlie, Vo, Ngoc, Watanabe, Nicholas M Donation intention in current students: An analysis of university engagement and sense of place in future athletic, academic, and split donors 2017 Journal of Issues in Intercollegiate Athletics ARTICLE Regression 2010-2019
David George {Vequist IV Nonprofit Fundraising Transformation through Analytics 2017 INCOLLECTION Social Media 2010-2019
Faisal, Ali An Investigation of the Relationship of Student Engagement to Alumni Giving at an Independent Technological University 2017 PHDTHESIS Regression 2010-2019
Kenneth D Lawrence, Stephan Kudyba, Sheila M Lawrence Funding Analytics: Predictive Analysis in a Major State Research University 2017 INCOLLECTION Regression 2010-2019 10.1108/S1477-407020170000012005
Liang Ye A machine learning approach to fundraising success in higher education 2017 MASTERSTHESIS Ensemble 2010-2019
AR Nandeshwar, R Devine Data Science for Fundraising: Build Data-driven Solutions Using R 2018 BOOK Other 2010-2019
Christian, Kelsey M Identifying Demographic Variables that can Predict Alumni Giving at a Regional Comprehensive Four-Year University in the South 2018 PHDTHESIS Regression 2010-2019
Day, Deborah A Factors in the Undergraduate Experience that Influence Young Alumni Giving 2018 PHDTHESIS Regression 2010-2019
Liu, Fangyao, Feng, Xixi, Ouyang, Qinge Factors Exploration on Alumni Donation: A Case Study of Creighton University 2018 Journal of Contemporary Management ARTICLE Regression 2010-2019
Natthawat Rattanamethawong, Sukree Sinthupinyo, Achara Chandrachai An innovation model of alumni relationship management: Alumni segmentation analysis 2018 Kasetsart Journal of Social Sciences ARTICLE Ensemble 2010-2019 10.1016/j.kjss.2017.02.002
U. N. Saraih, Nor Irwani Abdul Rahman, Norshahrizan Noordin, Sayang Nurshahrizleen Ramlan, Razli Ahmad, Mohd Fo’ad Sakdan, M. Harith Amlus Modelling Students’ Experience Towards the Development of Alumni Involvement and Alumni Loyalty 2018 MATEC} Web of Conferences ARTICLE Regression 2010-2019 10.1051/matecconf/201815005050
Lowe,LaKeisha D. Repeated College Alumni Giving: Application of the Commitment-Trust Theory of Relationship Marketing 2019 PHDTHESIS Regression 2010-2019
Naccarato,Shawn L. Predicting Alumni Giving at a Public Comprehensive Regional University: Predictive Multivariate Causal Models for Annual Giving, Significant Cumulative Giving, Major Giving, and Planned Giving 2019 PHDTHESIS Regression 2010-2019


Download a pre-print (and draft) version of this literature review.

About the Author

A co-author of Data Science for Fundraising, an award winning keynote speaker, Ashutosh R. Nandeshwar is one of the few analytics professionals in the higher education industry who has developed analytical solutions for all stages of the student life cycle (from recruitment to giving). He enjoys speaking about the power of data, as well as ranting about data professionals who chase after “interesting” things. He earned his PhD/MS from West Virginia University and his BEng from Nagpur University, all in industrial engineering. Currently, he is leading the data science, reporting, and prospect development efforts at the University of Southern California.