By: Matt Sifferlen
I recently read interesting articles on the Knowledge@Wharton and CNNMoney sites covering the land grab that’s taking place among financial services startups that are trying to use a consumer’s social media activity and data to make lending decisions. Each of these companies are looking at ways to take the mountains of social media data that sites such as Twitter, Facebook, and LinkedIn generate in order to create new and improved algorithms that will help lenders target potential creditworthy individuals. What are they looking at specifically? Some criteria could be:
- History of typing in ALL CAPS or all lower case letters
- Frequent usage of inappropriate comments
- Number of senior level connections on LinkedIn
- The quantity of posts containing cats or annoying self-portraits (aka “selfies”)
Okay, I made that last one up. The point is that these companies are scouring through the data that individuals are creating on social sites and trying to find useful ways to slice and dice it in order to evaluate and target consumers better.
On the consumer banking side of the house, there are benefits for tracking down individuals for marketing and collections purposes. A simple search could yield a person’s Facebook, Twitter, or LinkedIn profile. The behaviorial information can then be leveraged as a part of more targeted multi-channel and contact strategies.
On the commercial banking side, utilizing social site info can help to supplement any traditional underwriting practices. Reviewing the history of a company’s reviews on Yelp or Angie’s List could share some insight into how a business is perceived and reveal whether there is any meaningful trend in the level of negative feedback being posted or potential growth outlook of the company.
There are some challenges involved with leveraging social media data for these purposes.
1. Easily manipulated information
2. Irrelevant information that doesn’t represent actual likes, thoughts or relevant behaviors
From a Fraud perspective, most online information can easily and frequently be manipulated which can create a constantly moving target for these providers to monitor and link to the right customer. Fake Facebook and Twitter pages, false connections and referrals on LinkedIn, and fabricated positive online reviews of a business can all be accomplished in a matter of minutes. And commercial fraudsters are likely creating false business social media accounts today for shelf company fraud schemes that they plan on hatching months or years down the road. As B2B review websites continue to make it easier to get customers signed up to use their services, the downside is there will be even more unusable information being created since there are less and less hurdles for commercial fraudsters to clear, particularly for sites that offer their services for free.
For now, the larger lenders are more likely to utilize alternative data sources that are third party validated, like rent and utility payment histories, while continuing to rely on tools that can prevent against fraud schemes. It will be interesting to see what new credit and non credit data will be utilized as a common practice in the future as lenders continue their efforts to find more useful data to power their credit and marketing decisions.