Data analytics for risk forecast in financial industry

Data analytics is widely recognized in different financial sectors, such as risk forecasting and risk management, as one of the most promising parts of current economic advancement. Predictive algorithms have been proven as relevant methods for time-series modelling and forecasting in a significant number of successful applications. In this work a relative study of different predictive algorithms has been conducted in order to learn their performances in term of implementing financial time series forecasts. The Machine Hack-Financial Risk Prediction dataset has been used to examine overall performance of these algorithms and to predict whether an organization is under a possible financial risk or not.