Numerai-Data-science-problem

At the core of Numerai is a data science problem - the problem of predicting the stock market. In the provided training_data and tournament dataset, each id corresponds to a stock with a set of obfuscated features. The target represents future performance. Rows are grouped into eras that represent different points in time. We get the different dataset on every weekends and we have to submit our prediction on the numerai tournament. There are total 314 columns and rows more than 50000. In this challenge i have done feature selection to get only good feature for training and i left with with only 167 features from 311 features. For this challenge i have used neural network model by using keras and scikit learn library and used the hyperparameter for the better results. You can check the tournament on https://numer.ai/tournament and you will be able to check the dataset on the given link.