Forecasting during recession: Comparing the performance of machine learning and autoregressive models on the Swedish stock market
As the processing power of computers continuously increase so does the interest for machine learning and artificial intelligence. This thesis evaluates the forecasting performance of both machine learning models and common auto-regressive models on the Swedish stock market index OMXS30 on the Stockholm stock exchange during the 2008 financial crises. Forecasts are performed 3, 6 and 12 months ahea