| 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 the- sis 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. Moreover, we are taking order flow imbalance into account for the mid price modelling. Linear re- gression is used to model the possible linear relation between the order flow imbalance and price change in the limit order book. In the results we can see that an average accuracy score of 0.5 are achieved for multiple experiments. However, a majority of the models are prone to consequently classify the price change to be stationary. The LSTM neural network model achieves the highest precision score due to more variation in the predicted classes. |