Syoncloud released Big Data / Data Science solution for retail banks

LONDON - Nov. 8, 2013 - PRLog -- Syoncloud released Big Data / Data Science solution for retail banks. It covers areas such as individualization of product offers to existing clients, early fraud detection and fraud damage mitigation, prediction of products cancellations and client's defections, optimal allocation of cash to ATMs and bank branches, minimization of usage of expensive bank channels such as branch visits and reliable assessment of clients for debt products.

The key advantage of Syoncloud is to collect full datasets from backups and relational databases into Hadoop environment and apply ETL to standardize, cross link and validate data. Syoncloud applies machine learning technologies to find hidden patterns and correlations in data. Build in machine learning technologies use these patters to predict behaviour of customers, frauds, allocation of resources and business opportunities.

It utilizes primary data from banks such as bank accounts movements, direct debits, standing orders, ATM service logs, geographic locations of ATMs and bank branches, CRM information about clients, subscriptions to banks products and technical log files from Internet and mobile banking applications and call centre records.

Syoncloud creates a dataset of monthly expenses and incomes categories for all clients, all their accounts and complete history. Expense and income categories are fine grained such as housing, energy, restaurants, salaries, dividends, tax refunds, social benefits, rental income, sales and so on. Analysis of incomes and expenses enable individualization of product offers to existing clients. Banks save money on expensive broad marketing campaigns. Products will be offered only to customers that need them and are likely to accept them.

Early fraud detection and fraud damage mitigation includes detection of identity frauds, credit card frauds, wire frauds, attacks on internet and mobile banking and money laundering. New types of frauds and new schemes require flexible and fast detection algorithms. Statistical and rule based algorithms are no longer sufficient because they can only recognize known frauds and require expensive maintenance. We use complete history of all clients and machine learning algorithms such as clustering, neuronal networks, decision trees and classifications to find patterns and apply these patterns on new transactions.

In order to reliably assess risks of debt products Syoncloud takes into account not just current credit scores and current disposable income of the clients but also complete history of the client as well as social context. This decreases risk for the bank and increases income from valuable clients who would be otherwise rejected. Syoncloud uses dataset of incomes and expenses, complete history of payment morale for credit cards, consumer loans, mortgages, overdrafts and other debt products and CRM information about clients. It utilizes machine learning algorithms such as Markov Chain to predict future payment morale. Predictions are verified against historical data of profitable and defaulted loans, credit cards and other debt products. We have achieved 46% improved of reliability compared to pure credit scores.

Prediction of bank products cancellations and client's defections is very time sensitive. Bank has just days to act before client irreversibly decide to cancel a product or move to competition. Bank needs to identify clients who are likely to defect, contact them and pro-actively offer alternative products or solve client's issues. It is much cheaper to retain highly profitable clients than to attract them back. Syoncloud utilizes account movements, debit and credit card movements, clients dataset from CRM, product subscription dataset, call centre and branch visits transactions and log information as primary data sources for predictions.

Demand for cash is highly variable during year at many ATMs and bank branch locations. The variability is caused by weather, local events, vacations, tourism and so on. It is important to predict right amount cash that needs to be deposited into ATMs as well as bank branches. It is costly to service ATMs too often, it is also costly to have cash machines out of order due lack of cash. In the same time we want to limit amount of unnecessary cash that is stored for long times in ATMs and bank branches. It leads to suboptimal cash allocation as well as it attracts crime. Syoncloud uses ATM service logs, geographic locations of ATMs and bank branches, withdraws dataset for each ATM, weather reports for ATMs and bank branch locations, schedules of sports, cultural or other events as well as holidays for all locations. It also utilizes credit and debit card movements to assess demand for cash at various locations and during different times of the year.

More information is available at http://www.syoncloud.com/Syoncloud_Big_Data_for_Retail_Ba...