Big Data Scoring

Scoring Big Data is a cloud-based Service That lets consumer loan Lenders Improve quality and acceptance rates through the use of big data . The company was founded in 2013 and has offices in UK , Finland , Chile , Indonesia and Poland . The company ‘s services are aimed at all lenders – banks , payday lenders , peer – to – peer lending platforms , microfinance providers and leasing companies . [1]

Big data based on credit scoring models

Based on Facebook information

On April 9, 2013, the company announced that they have built a credit scoring model based purely on information from Facebook . According to the company, the scoring model has a Gini coefficient of 0.340. In order to build the model, the data is collected in various European countries. This data was then combined with the information provided by the United States and the United States. [2]

Based on open source sources

Big Data Scoring collects large amounts of data from sources and uses it to predict individuals’ behavior by applying proprietary data processing and scoring algorithms . Based on customer feedback, their solution delivers an improvement of up to 25% in scoring accuracy when combined with traditional in-house methods . This is robustly translated to an equivalent increase in the bottom line . [3] In markets where traditional credit bureau data is lacking, the added benefit can be even greater than or equal to no credit history, for example:

  • young people
  • unbanked and underbanked
  • recent immigrants

This results in a better way to improve the accuracy of scoring model accuracy.

Predictive powers of big data in credit scoring

Facebook information

The company is not the first to show the predictive powers of Facebook data. Michal Kosinskia, David Stillwella, and Thore Graepelb from University of Cambridge have shown that “easily accessible digital records of behavior, Facebook Likes, can be used to automatically and accurately predict a range of highly sensitive personal attributes including: sexual orientation, ethnicity, religious and political views, personality traits, intelligence, happiness, use of addictive substances, parental separation, age, and gender. [4] ”

Public sources

Filene Research Institute published a paper showing clear patterns in transactional data, credit score and external factors like the recent price of S & P 500 . [5]

Press coverage and acknowledgments

In October 2013, Big Data Scoring was selected as a finalist of the Websummit exhibition start-up ALPHA program. [6] In March 2013, Big Data Scoring was selected as one of the finalists of the Code_n competition, which is part of the CeBIT exhibition in Hannover, Germany. [7] During Finovate Fall 2015 the CEO of Big Data Scoring presented their solutions live on stage. [8] The company has featured in many online magazines, including MarketWatch , [9]PCWorld [10] and eWeek . [11]

Big Data Scoring is working together with MasterCard in their Start Path program. [12]

Criticism

Estonian business daily Äripäev raised the question of data mining . According to the company, their solution requires a permission from the users of Facebook to access their data. [13] Other sources Such As MSN News -have Cited invasion of privacy have an additional concern Regarding using social media information in credit scoring. [14]

References

  1. Jump up^ “Big Data Scoring” . Company web page.
  2. Jump up^ “First Ever Generic European Social Media Scorecard Ready” . Company web page. 9 April 2013. Archived from the original on 2014-05-29.
  3. Jump up^ “Case Study on a European Data Center: Big Data Scoring | The Leader in Big Data Credit Scoring Solutions” . www.bigdatascoring.com . Archived from the original on 2015-10-22 . Retrieved 2015-11-27 .
  4. Jump up^ Kosinski, Michal; David Stillwell; Thore Graepel (February 12, 2013). “Private traits and attributes are predictable from digital records of human behavior” (PDF) : 4.
  5. Jump up^ Kallerhoff, Philipp (2013). “Big Data and Credit Unions: Machine Learning in Member Transactions” (PDF) . Filene Research Institute . Retrieved 25 November 2015 .
  6. Jump up^ “WebSummit ALPHA Finalist List” (PDF) .
  7. Jump up^ “List of CODE_n finalists” (PDF) . Archived from the original (PDF)on 2014-05-27.
  8. Jump up^ “FinovateFall 2015 – Big Data Scoring – Finovate” . Finovate . Retrieved 2015-11-27 .
  9. Jump up^ “When Facebook is bad for one’s credit rating” . MarketWatch . Retrieved March 13, 2014 .
  10. Jump up^ “Should your Facebook profile influence your credit score? Startups say yes” . PCWorld . Retrieved March 11, 2014 .
  11. Jump up^ “CeBIT Code_n Exhibit Shows Why Useful Innovation Is the Best Kind” . eWeek . Retrieved March 13, 2014 .
  12. Jump up^ “Portfolio | Start Path” . www.startpath.com . Retrieved 2015-11-27 .
  13. Jump up^ “We Are Not Mining Data From Social Media Illegally” . Baltic Business News. May 8, 2013.
  14. Jump up^ “Rumor: Facebook ‘likes’ can hurt your credit score” . MSN News . Retrieved August 27, 2013 .