Deep learning for wealth management
Tech-savvy wealth management and robo-advisors are becoming more and more hyped in the financial world. Banks and financial institutions keep extensive databases of their clients and investments, which can be used to assist them better in their investment and funds allocations strategies. In a world where big data offer ever more analysis and prediction potential, the challenge is to verify if, by using a larger amount of data, it is possible to create an automatic system to predict, given a subset of MIFID interview data and demographic information about each client, their preferred funds allocations among different investments types.
Axyon's technology was used to process anonymized clients and investments data, normalize them and use them to develop a prediction model based on Deep Learning techniques. The client provided Axyon with the investments types to use as target classes. The rapid development of Deep Learning models, evolved and trained using the Axyon Platform, allowed for the setup of a fully working system that can be easily integrated into the client’s IT infrastructure.
The system returns the predicted funds allocations of the client between 5 types of investment categories (e.g. mutual funds, life insurance, cash accounts, etc.).
Axyon demonstrated to be able to build and develop predictive models extremely powerful which can be easily integrated into an existing system.