Use Cases Industry: Banking
ATM service optimization
The ATM service can be improved through the use of Esplores and big data. For example, combining the data on the optimal recharge period and the cash money actually available in the ATMs. The combination of these data with the prediction of withdrawals on the basis of information regarding the flow of people, the position of ATMs and other factors. Esplores allows the management of very deep historical data and the integration with statistical models and external algorithms in order to allow very effective analytics. This process, if well structured, can allow banks to optimize the management of ATMs thanks to correct predictions of how much cash could be needed for each individual ATM.
IMPROVE CUSTOMER RELATIONSHIPS
Often the customers of a bank are "classified" and associated with a group defined according to more or less generic aggregation methods. Esplores makes it possible to identify groups with high precision benchmarking in a dynamic and more accurate way.
Explores can integrate the indicators already used by the bank with other external data (e.g., unstructured public data deriving from personal social profiles or, in a business-to-business context, deriving from on-line newspapers, etc.).
Best next offer
Esplores allows the analysis of various types of data facilitating the client’s knowledge and behavior. By analysing some factors, such as answers to past offers, creditworthiness, personal information, personal preferences and more general information, as well as how other similar customers have responded to the offers, you can customise the offer and increase customer loyalty.
To assess credit risk, a bank usually bases customer evaluation on a series of quantitative indicators. Esplores allows the implementation of multiple indicators and , in some cases, the support of the risk analysis with a descriptive analysis.
Anti-money laundering solutions typically are based on the application of money flow detection models. Esplores can allow a wider "vision" on the data, for example, by analysing the known fields and discovering hidden correlations between various subjects, with the possibility of analysing data even in real-time so as to intervene in a timely manner in intercepting possible "non transparent" transactions.