Implementation of Robo-Advisor Services for Different Risk Attitude Investment Decisions Using Machine Learning Techniques

In this paper we have researched how to use machine learning in the financial industry on the example of robo-advisor; defined the basic functionality of robo-advisor, an implementation of robo-advisor based on analysis of the most popular financial services, such as Betterment, FutureAdvisor, Motif Investing, Schwab Intelligent and Wealthfront. We have also compared their functionality, formulated a list of critical features and described our own high-level architecture design of a general robo-advisor tool for private investors. Our goal is to build three application modules for a single robo-advisor which combines its architecture and modern financial instruments – cryptocurrencies for the first time. The first module is a Long short-term memory (LSTM) neural network, which forecasts cryptocurrencies prices daily. As a result of simulation experiment through the application using real data from open sources, we have found that the combination of criterion can explain 61% of cryptocurrencies prices variation. The second module uses robo-advising approach to build an investment plan for novice cryptocurrencies investors with different risk attitude investment decisions. The third module is ETL (Extract-Transform-Load) for a statistics dataset and neural networks models. Results of the investigation show that investing in cryptocurrencies can give 23.7% per year for risk-averse, 31.8% per year for risk-seeking investors and 16.5% annually for investors of hybrid type.