I know it's a general question but what type of analytics can be done in this case? How can we apply machine learning models here?


Common use cases include:

  1. Fraud detection
  2. Transactions volume prediction
  3. Next transaction date

Fraud detection

This is usually tackled with anomaly detection.

It requires information on the two transaction parties and using machine learning to figure out when a transaction is out of the norm and flagging as a potential case of fraud.

Transactions volume prediction

This is usually tackled with time-series forecasting.

The idea is to predict the amount of transaction that will be done in the next day/week/month for a large amount of users. It requires seasonal information and, in case you have a lot of C2B transactions, analysis on major business.

Next transaction date

This is also usually tackled with time-series forecasting. However, this analysis can be done on individual levels and not necessarily on a group of users.

The idea is to predict the date that the next transaction will be executed. This can be useful because there are cases where users will perform a lot of transactions in a short period of time, which could may be grouped together.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.