Agata advances social lending, credit scoring with SAS® Text Analytics

Traditional channels for obtaining credit, with their standardized, depersonalized procedures, are not always perfectly in tune with the rapid evolution of lifestyles and careers. Operators are beginning to realize this fact.

On the other hand, it is increasingly difficult for investors to find opportunities that are both transparent and profitable. Why not then create a common space in which credit supply and demand can come together to benefit each other? This is, in effect, the idea behind Prestiamoci.it.

An innovative marketplace model recently launched by Agata, Prestiamoci.it takes advantage of Web 2.0 interactivity and social networking tools to reap the full potential of a loan.

A community where credit demand meets credit supply 
Prestiamoci.it is structured as a community in which lenders consciously divide their investments among projects that are in line with their perspectives and objectives to diversify and mitigate risk. Meanwhile, prospective borrowers are able not only to obtain significant funding without depending on a single source, but also to receive suggestions and advice from lenders interested in the successful outcome of the project.

"The basic idea behind our initiative," explains Agata Chairman Paolo Galvani, "is to adapt the social lending paradigm by taking advantage both of the typical peer-to-peer model and Web 2.0 technologies, such as social networks and communities. It is a matter of building a virtual meeting place where individuals looking for financing and those who want to invest money can meet and interact without any outside intervention. Or at least, with as little intervention as possible, as the bank continues to play a fundamental role as guarantor of the transactions. In short, it is the modern equivalent of the most ancient form of credit – that is, a loan between private parties: One individual seeks financing in order to carry out a project that is useful to him and others, while another individual lends the money, and a virtuous cycle of debt begins."

Behind every loan there is a project 
The community-based framework that inspired Prestiamoci.it not only emphasizes the relational aspect of lending, i.e., interpersonal interactions, but also affects the structural organization of the marketplace. As Agata CEO Mariano Carozzi explains, "Individuals seeking a loan, owners of small commercial or craft business in particular, do not just post their request on a bulletin board, but instead provide a description of their project, for instance, its objectives, methods of implementation and possible areas for expansion. Investors, on the other hand, in addition to providing the information required by law, also must express their own preferences regarding the areas with which they feel a closer bond and that they wish to finance." From a functional and technological standpoint, the marketplace should therefore ensure optimal pairing of investments with projects, as well as assessment of credit risk based not only on traditional criteria, but also on typical community values. This is where SAS' cooperation has proven vital.

Marketplace optimization
"Our challenge," continues Galvani, "was to implement a totally new model. SAS has been an invaluable partner for us because, with their ability to adapt themselves to the context, they helped us both to improve our ideas and models through discussion and comparison and to transform the marketplace into a concrete solution, with its own restrictions and objectives." The adoption of advanced optimization techniques was key to maximizing the effectiveness of the interactions between prospective borrowers and investors while complying with certain predefined restrictions.

For instance, investments must be distributed over several projects in order to mitigate risk and must account for the order in which requests and offers are submitted. It is necessary both to diversify investments and minimize the number of lenders for each project in order to control transaction expenses. Furthermore, lenders must also have the freedom to choose their preferred areas of investment and select projects that are most in line with their ways of thinking.

Text mining to align credit ratings with community values
The calculation and attribution of credit ratings, tasks that were already extremely complicated, must also fulfill the new criteria that form the basis of the community model. "Ratings assessment is, in general, quite standardized, as it is based on quantitative variables from past history and on defined risk categories," explains Carozzi. "Our objective was to combine traditional scoring with a qualitative evaluation of the data available.

"This is possible because prospective borrowers, especially in the case of small business owners, not only state the amount of credit needed, but also provide both personal and project-related information, i.e., its objectives, methods of implementation and possible areas for expansion." The use of SAS® Text Miner made it possible to analyze unstructured data and interpret the traditional score, thanks to additional information from community participants and their experience profile taken from the Web.

Efficient models for credit negotiation 
Is it already possible to formulate a preliminary assessment of the project? "We have not yet put the platform into practice and opened it to the public, something we will be doing shortly, but we are convinced, in any case, that this technological development will open new doors to more efficient credit negotiation models," says Carozzi.

"Our efforts are an initial attempt to allow individuals to talk directly, thereby shortening the value chain. For the time being, we can say that we have designed and developed an extremely efficient social lending initiative from a perspective of diversification and reconciliation between credit supply and demand.

"Additionally, by adopting text mining techniques, we were able not only to align rating calculation criteria with the goals and values that characterize the Prestiamoci.it community, but also to offer those who approach our marketplace greater possibilities in comparison to other P2P lending initiatives, for instance by broadening the scope of eligible entities."
 
 

 

The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.

Copyright © SAS Institute Inc. All Rights Reserved.