Is an Offline Sharing Economy Innovation Transmissible Online?

Group lending is a social innovation because the substitution of the guarantee on assets by the collective guarantee of the group of belonging leads to the financial inclusion of the excluded. In a lending group, members who know each other mutually control each other to guarantee repayment of the loan and its circulation among the members. Is the social collateral that supported the development of the offline microcredit to the world level transposable to social lending on the internet? To answer this question, this chapter aims at determining the factors of mutual supervision and control of the members within the affiliation group and examine the potential of their transposition on the internet. Understanding the conditions for transposing social security is not only a solution to the problem of the unbanked; it is also a source of inspiration for peer-to-peer activities which develop considerably on the internet.

SME Financing in MENA: A Quantitative and Qualitative Analysis of Multilateral and Bilateral Development Lenders’ Intermediated Lending Practices

This paper documents for the first time the considerable increase of bilateral and multilateral financial institutions’ support to small- and medium-sized enterprises (SMEs) in the Middle East and North Africa (MENA), following the political unrest and civil strife across the region since 2011. Focusing upon intermediated lending, the main financing channel, it assesses the underlying economic logic and implementation of this kind of SME financing. It is found that SMEs’ contribution to economic development is insufficiently well understood and, to some extent, has been misinterpreted, which implies that development banks’ lending operations lack appropriate targeting to achieve economic and social lending objectives. A review of the academic literature on financial exclusion and development finance, moreover, concludes that the lenders’ reliance upon large, often foreign-owned, commercial banks is not likely to achieve the desired developmental impact.

In Search of Crowdfunding Business Models

Crowdfunding platforms have substantially increased since 2005 and have supported entrepreneurial projects in response to the low propensity of banking institutions to finance either startups, or poor or young entrepreneurs. However, the theory of strategies and management of crowdfunding is far behind the dynamism of its growth. This shortcoming most likely causes costs and failures, in particular during the current state of increasing competitive pressure in the sector. This paper seeks to construct a general theoretical definition for the concept of a business model and apply it to the P2P social lending on the Internet. Extensive literature is reviewed to construct an archetype business model. The validity of the model will be tested through crowdfunding platforms.

Towards Repayment Prediction in Peer-to-Peer Social Lending Using Deep Learning

Peer-to-Peer (P2P) lending transactions take place by the lenders choosing a borrower and lending money. It is important to predict whether a borrower can repay because the lenders must bear the credit risk when the borrower defaults, but it is difficult to design feature extractors with very complex information about borrowers and loan products. In this paper, we present an architecture of deep convolutional neural network (CNN) for predicting the repayment in P2P social lending to extract features automatically and improve the performance. CNN is a deep learning model for classifying complex data, which extracts discriminative features automatically by convolution operation on lending data. We classify the borrower’s loan status by capturing the robust features and learning the patterns. Experimental results with 5-fold cross-validation show that our method automatically extracts complex features and is effective in repayment prediction on Lending Club data. In comparison with other machine learning methods, the standard CNN has achieved the highest performance with 75.86%. Exploiting various CNN models such as Inception, ResNet, and Inception-ResNet results in the state-of-the-art performance of 77.78%. We also demonstrate that the features extracted by our model are better performed by projecting the samples into the feature space.

A Boosted Decision Tree Model for Predicting Loan Default in P2P Lending Communities

Loan Default Prediction For Social Lending Is An Emerging Area Of Research In Predictive Analytics. The Need For Large Amount Of Data And Few Available Studies In The Current Loan Default Prediction Models For Social Lending Suggest That Other Viable And Easily Implementable Models Should Be Investigated And Developed. In View Of This, This Study Developed A Data Mining Model For Predicting Loan Default Among Social Lending Patrons, Specifically The Small Business Owners, Using Boosted Decision Tree Model. The United States Small Business Administration (Usba) PubliclyAvailable Loan Administration Dataset Of 27 Features And 899164 Data Instances Was Used In 80:20 Ratios For The Training And Testing Of The Model. 16 Data Features Were Finally Used As Predictors After Data Cleaning And Feature Engineering. The Gradient Boosting Decision Tree Classifier Recorded 99% Accuracy Compared To The Basic Decision Tree Classifier Of 98%. The Model Is Further Evaluated With (A) Receiver Operating Characteristics (Roc) And Area Under Curve (Auc), (B) Cumulative Accuracy Profile (Cap), And (C) Cumulative Accuracy Profile (Cap) Under Auc. Each Of These Model Performance Evaluation Metrics, Especially Roc-Auc, Showed The Relationship Between The True Positives And False Positives That Implies The Model Is A Good Fit.