Predicting Asset Indexes for Safe and Profitable Portfolio Allocation

Sammanfattning: Many investors face the complicated task of allocating and forecasting asset indexes in asafe and profitable manner. The primary objective of this bachelor thesis is to introduce asafe and risk-adjustment portfolio allocation, consisting of four Swedish listed. In order toenhance the profitability of the portfolio, the asset indexes will be predicted one day intothe future. The machine learning algorithm, which is a commonly used for detecting trendsin time-based data, will be implemented in favor of achieving this task. The efficacy of theused LSTM model was evaluated and produced varying results, which indicated thelimitation of only predicting one day ahead.