ESTIMATING BITCOIN BUYING AND SELLING MOMENTS USING DECISION TREES

Abstract

The popularity of bitcoin has aroused the interest of investors in the cryptocurrency market, however, many end up in debt for the mistakes made. In view of this, the purpose of this work is develop a model that can help novice investors in their decisions to buy and sell bitcoins through the decision tree technique and graphic indicators. The model tested the technique's ability to learn and predict with simulations and cross-validation. The results showed that it was possible to generate positive feedback in the simulations over the cryptocurrency's historical period, where the algorithm was able to generate operations that added significant profit in the long term.