Predicting donation behavior: Acquisition modeling in the nonprofit sector using Facebook data (original) (raw)
Related papers
E3S Web of Conferences
Customer behavior classification can be useful to assist companies in conducting business intelligence analysis. Data mining techniques can classify customer behavior using the K-Nearest Neighbor algorithm based on the customer's life cycle consisting of prospect, responder, active and former. Data used to classify include age, gender, number of donations, donation retention and number of user visits. The calculation results from 2,114 data in the classification of each customer’s category are namely active by 1.18%, prospect by 8.99%, responder by 4.26% and former by 85.57%. System accuracy using a range of K from K = 1 to K = 20 produces that the highest accuracy is 94.3731% at a value of K = 4. The results of the training data that produce a classification of user behavior can be used as a Business Intelligence analysis that is useful for companies in determining business strategies by knowing the target of optimal market.
Predicting Donations from a Cohort Group of Donors to Charities
International Journal of Operations Research and Information Systems, 2011
Charity fundraising organizers increasingly attempt to predict the donations to their causes to maximize the effectiveness of their expenditures and achieve their “social good” objectives. Much of the scholarly work in cause-related fundraising uses organization-specific demographic, geographic, psychographic and behavioral information about its donors to forecast donation amounts. Instead of distinguishing the potential donors, this study focuses on the prediction of the donations from existing donors. Specifically, a large dataset containing four years worth of transactional, appeals, source, and donor data related to a leading U.S. charitable organization was made available to the authors by the Direct Marketing Educational Foundation. The current paper contributes to the literature on donor lifetime value by documenting, in the context of a case study, the results of seven models for predicting future contributions using historic data over four years related to the cohort group ...
Using machine learning approach towards successful crowdfunding prediction
Bulletin of Electrical Engineering and Informatics, 2023
Crowdfunding is a concept that emerged due to difficulties in raising funds for community business projects, social activities, micro-enterprises, and start-ups conventionally. Crowdfunding uses internet technology as a bridge between the donor and the recipient of funds so that it can reach a wider range of donors. This study aims to compare the performance of machine learning approaches in predicting crowdfunding campaign success. Three machine learning algorithms were employed to predict crowdfunding campaign success, namely logistic regression, random forest, and extreme gradient boosting (XGBoost). The dataset used in this study contains data about all projects posted on Kickstarter from January 2020 to September 2022. To improve the prediction model's performance, experiments using principal component analysis (PCA) feature reduction and log transformation were conducted. The results show that the implementation of log transformation on the dataset can increase the prediction model's performance. Meanwhile, XGBoost algorithm performs better than linear regression and random forest.
IRJET- Paid Commercial on Facebook: An Estimation Using a Data Mining Approach
IRJET, 2020
This paper focuses on evaluating the performance of paid publications (paid ads) on Facebook and proposes a managerial implication to maximize the paid publications' performance in reaching as many people as possible with the greatest possible engagement. Artificial neural networks, Garson's algorithm, and support vector machine weighting were wont to analyze publication characteristics. The results demonstrate that in terms of number of people reached, paid publications are only 9.52% relevant, compared with 24.35% for post hour, 16.85% for total page likes, and 16.44% for type of publication. With regards to quantity of comments, likes, and shares, paid commercial contributes 10.46%, 19.51%, and 15.55% relevance, respectively. Additionally, the vital numbers of e-book enhancements from the use of paid advertisements and non-paid advertisements are in contrast and calculated. This paper provides a managerial implication for marketing managers to enhance the paid ad performance of company Facebook pages.
Analysis and Outcome Prediction of Crowdfunding Campaigns
International Journal of Information Retrieval Research
Humongous volumes of data are being generated every minute by individual users as well as organizations. This data can be turned into a valuable asset only if it is analyzed, interpreted and used for improving processes or for benefiting users. One such source that is contributing huge data every year is a large number of web-based crowd-funding projects. These projects and related campaigns help ventures to raise money by acquiring small amounts of funding from different small organizations and people. The funds raised for crowdfunded projects and hence, their success depends on multiple elements of the project. The current work predicts the success of a new venture by analysis and visualization of the existing data and determining the parameters on which success of a project depends. The prediction of a project’s outcome is performed by application of machine learning algorithms on crowd-funding data stored in the NoSQL database, MongoDB. The results of this work can prove benefic...
Success in an Online Giving Day: The Role of Social Media in Fundraising
Nonprofit and Voluntary Sector Quarterly
Social media platforms offer nonprofits considerable potential for crafting, supporting, and executing successful fundraising campaigns. How impactful are attempts by these organizations to utilize social media to support fundraising activities associated with online Giving Days? We address this question by testing a number of hypotheses of the effectiveness of using Facebook for fundraising purposes by all 704 nonprofits participating in Omaha Gives 2015. Using linked administrative and social media data, we find that fundraising success—as measured by the number of donors and value of donations—is positively associated with a nonprofit’s Facebook network size (number of likes), activity (number of posts), and audience engagement (number of shares), as well as net effects of organizational factors including budget size, age, and program service area. These results provide important new empirical insights into the relationship between social media utilization and fundraising success...