Understanding and promoting micro-finance activities in Kiva.org

Jaegul Choo, Changhyun Lee, Daniel Lee, Hongyuan Zha, Haesun Park

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

Abstract

Non-profit Micro-finance organizations provide loaning opportunities to eradicate poverty by financially equipping impoverished, yet skilled entrepreneurs who are in desperate need of an institution that lends to those who have little. Kiva.org, a widely-used crowd-funded micro-financial service, provides researchers with an extensive amount of publicly available data containing a rich set of heterogeneous information regarding micro-financial transactions. Our objective in this paper is to identify the key factors that encourage people to make micro-financing donations, and ultimately, to keep them actively involved. In our contribution to further promote a healthy micro-finance ecosystem, we detail our personalized loan recommendation system which we formulate as a supervised learning problem where we try to predict how likely a given lender will fund a new loan. We construct the features for each data item by utilizing the available connectivity relationships in order to integrate all the available Kiva data sources. For those lenders with no such relationships, e.g., first-time lenders, we propose a novel method of feature construction by computing joint nonnegative matrix factorizations. Utilizing gradient boosting tree methods, a state-of-the-art prediction model, we are able to achieve up to 0.92 AUC (area under the curve) value, which shows the potential of our methods for practical deployment. Finally, we point out several interesting phenomena on lenders' social behaviors in micro-finance activities.

Original languageEnglish
Title of host publicationWSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining
PublisherAssociation for Computing Machinery
Pages583-592
Number of pages10
ISBN (Print)9781450323512
DOIs
Publication statusPublished - 2014 Jan 1
Externally publishedYes
Event7th ACM International Conference on Web Search and Data Mining, WSDM 2014 - New York, NY, United States
Duration: 2014 Feb 242014 Feb 28

Publication series

NameWSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining

Conference

Conference7th ACM International Conference on Web Search and Data Mining, WSDM 2014
CountryUnited States
CityNew York, NY
Period14/2/2414/2/28

Fingerprint

Finance
Trees (mathematics)
Recommender systems
Supervised learning
Factorization
Ecosystems

Keywords

  • cold-start problem
  • crowdfunding
  • gradient boosting tree
  • heterogeneous data
  • joint matrix factorization
  • microfinance
  • recommender systems

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Choo, J., Lee, C., Lee, D., Zha, H., & Park, H. (2014). Understanding and promoting micro-finance activities in Kiva.org. In WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining (pp. 583-592). (WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining). Association for Computing Machinery. https://doi.org/10.1145/2556195.2556253

Understanding and promoting micro-finance activities in Kiva.org. / Choo, Jaegul; Lee, Changhyun; Lee, Daniel; Zha, Hongyuan; Park, Haesun.

WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, 2014. p. 583-592 (WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Choo, J, Lee, C, Lee, D, Zha, H & Park, H 2014, Understanding and promoting micro-finance activities in Kiva.org. in WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining. WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining, Association for Computing Machinery, pp. 583-592, 7th ACM International Conference on Web Search and Data Mining, WSDM 2014, New York, NY, United States, 14/2/24. https://doi.org/10.1145/2556195.2556253
Choo J, Lee C, Lee D, Zha H, Park H. Understanding and promoting micro-finance activities in Kiva.org. In WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery. 2014. p. 583-592. (WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining). https://doi.org/10.1145/2556195.2556253
Choo, Jaegul ; Lee, Changhyun ; Lee, Daniel ; Zha, Hongyuan ; Park, Haesun. / Understanding and promoting micro-finance activities in Kiva.org. WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, 2014. pp. 583-592 (WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining).
@inproceedings{6c7a7adc799249f990ea17e6439d8561,
title = "Understanding and promoting micro-finance activities in Kiva.org",
abstract = "Non-profit Micro-finance organizations provide loaning opportunities to eradicate poverty by financially equipping impoverished, yet skilled entrepreneurs who are in desperate need of an institution that lends to those who have little. Kiva.org, a widely-used crowd-funded micro-financial service, provides researchers with an extensive amount of publicly available data containing a rich set of heterogeneous information regarding micro-financial transactions. Our objective in this paper is to identify the key factors that encourage people to make micro-financing donations, and ultimately, to keep them actively involved. In our contribution to further promote a healthy micro-finance ecosystem, we detail our personalized loan recommendation system which we formulate as a supervised learning problem where we try to predict how likely a given lender will fund a new loan. We construct the features for each data item by utilizing the available connectivity relationships in order to integrate all the available Kiva data sources. For those lenders with no such relationships, e.g., first-time lenders, we propose a novel method of feature construction by computing joint nonnegative matrix factorizations. Utilizing gradient boosting tree methods, a state-of-the-art prediction model, we are able to achieve up to 0.92 AUC (area under the curve) value, which shows the potential of our methods for practical deployment. Finally, we point out several interesting phenomena on lenders' social behaviors in micro-finance activities.",
keywords = "cold-start problem, crowdfunding, gradient boosting tree, heterogeneous data, joint matrix factorization, microfinance, recommender systems",
author = "Jaegul Choo and Changhyun Lee and Daniel Lee and Hongyuan Zha and Haesun Park",
year = "2014",
month = "1",
day = "1",
doi = "10.1145/2556195.2556253",
language = "English",
isbn = "9781450323512",
series = "WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining",
publisher = "Association for Computing Machinery",
pages = "583--592",
booktitle = "WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining",

}

TY - GEN

T1 - Understanding and promoting micro-finance activities in Kiva.org

AU - Choo, Jaegul

AU - Lee, Changhyun

AU - Lee, Daniel

AU - Zha, Hongyuan

AU - Park, Haesun

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Non-profit Micro-finance organizations provide loaning opportunities to eradicate poverty by financially equipping impoverished, yet skilled entrepreneurs who are in desperate need of an institution that lends to those who have little. Kiva.org, a widely-used crowd-funded micro-financial service, provides researchers with an extensive amount of publicly available data containing a rich set of heterogeneous information regarding micro-financial transactions. Our objective in this paper is to identify the key factors that encourage people to make micro-financing donations, and ultimately, to keep them actively involved. In our contribution to further promote a healthy micro-finance ecosystem, we detail our personalized loan recommendation system which we formulate as a supervised learning problem where we try to predict how likely a given lender will fund a new loan. We construct the features for each data item by utilizing the available connectivity relationships in order to integrate all the available Kiva data sources. For those lenders with no such relationships, e.g., first-time lenders, we propose a novel method of feature construction by computing joint nonnegative matrix factorizations. Utilizing gradient boosting tree methods, a state-of-the-art prediction model, we are able to achieve up to 0.92 AUC (area under the curve) value, which shows the potential of our methods for practical deployment. Finally, we point out several interesting phenomena on lenders' social behaviors in micro-finance activities.

AB - Non-profit Micro-finance organizations provide loaning opportunities to eradicate poverty by financially equipping impoverished, yet skilled entrepreneurs who are in desperate need of an institution that lends to those who have little. Kiva.org, a widely-used crowd-funded micro-financial service, provides researchers with an extensive amount of publicly available data containing a rich set of heterogeneous information regarding micro-financial transactions. Our objective in this paper is to identify the key factors that encourage people to make micro-financing donations, and ultimately, to keep them actively involved. In our contribution to further promote a healthy micro-finance ecosystem, we detail our personalized loan recommendation system which we formulate as a supervised learning problem where we try to predict how likely a given lender will fund a new loan. We construct the features for each data item by utilizing the available connectivity relationships in order to integrate all the available Kiva data sources. For those lenders with no such relationships, e.g., first-time lenders, we propose a novel method of feature construction by computing joint nonnegative matrix factorizations. Utilizing gradient boosting tree methods, a state-of-the-art prediction model, we are able to achieve up to 0.92 AUC (area under the curve) value, which shows the potential of our methods for practical deployment. Finally, we point out several interesting phenomena on lenders' social behaviors in micro-finance activities.

KW - cold-start problem

KW - crowdfunding

KW - gradient boosting tree

KW - heterogeneous data

KW - joint matrix factorization

KW - microfinance

KW - recommender systems

UR - http://www.scopus.com/inward/record.url?scp=84906877456&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906877456&partnerID=8YFLogxK

U2 - 10.1145/2556195.2556253

DO - 10.1145/2556195.2556253

M3 - Conference contribution

AN - SCOPUS:84906877456

SN - 9781450323512

T3 - WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining

SP - 583

EP - 592

BT - WSDM 2014 - Proceedings of the 7th ACM International Conference on Web Search and Data Mining

PB - Association for Computing Machinery

ER -