Intraday price prediction of Nordic stocks with limit order book data

Sammanfattning: Predicting the direction of mid price changes could facilitate the decision of when in time an order should be placed on the market. The purpose of this thesis is to evaluate modelling approaches used to classify the direction of mid price changes in the limit order book on short term. Multi-layer perceptron and long short-term memory neural networks are evaluated with two sets of features derived from Nordic limit order book data. When classifying the direction of the mid price on Swedish stock data, an average accuracy score of 0.5 is achieved for multiple of the experiments, which is significant better than the accuracy achieved by the random classifier. However, a majority of the models are prone to consequently classify the price change to be stationary. The results show that including the order flow imbal- ance in the set of features does not improve the predictability of the models. Moreover, we are taking order flow imbalance into account for the mid price modelling. Linear regression is used to model the possible linear relation between the order flow imbalance and price change in the limit order book. Using the model to classify the price change direction results in an accuracy score of 0.36, a value close to the by chance accuracy.