The field of finance is an interesting field in which much research takes place. In particular, its sub-field of modeling the dynamics of order books is an interesting field, since it translates into modeling the behaviour of traders on the market. Most of the models proposed in this field can be divided into stochastic models or machine learning models. The problem with the former ones is that they often make assumptions that do not propagate to practical applications, while the problem with the latter is that the models are often incomprehensible, even though they yield good results. This work tries to combine both of those fields to maintain the transparency of stochastic models and the accuracy of machine learning models. We target the limit order book, which is a book used in financial markets to place orders for financial securities in. It is a challenge to both generate realistic order books and predict them as well, since the model should be able to understand the underlying dynamics of order books to do this. We present a deep-learning-based model that is able to generate order books, through the use of a generative adversarial network (GAN) like architecture, and is able to predict order books using a similar architecture for the generator. Our models are able to outperform traditional generative and predictive models in both instances, while it remains transparent in its calculation: it is still able to extract useful and interpretable features from the underlying data set. These features, like the probabilities for up or down movements, or stagnations, or the rates at which the variables within the order book move, can be used by traders or algorithms to make sense out of the predictions. Traders can, for example, ask themselves whether the extracted features are representative of the analyzed asset and can, through this question, build additional confidence in the model. Another use case could be to utilize those features as inputs to other models. To our knowledge, this is the first work that proposes a combination of a stochastic and machine learning model to learn the dynamics of the order book.

Time series forecasting has been proved to be relatively easier for stationary time series, compared to non-stationary time series. This research proposes a method to partially omit the non-stationarity of the data using prioritized sampling. Using multiple feature selection methods in combination with a random forest regressor (RFR), we aim to predict the values for a non-stationary time series. In particular, the principal component analysis (PCA), kernel PCA, incremental PCA and independent component analysis methods are used. The features extracted from these methods will be fed into an RFR both individually and combined, using the union and intersection operators. The features given by the IPCA ∪ PCA ∪ KPCA method, using prioritized sampling with multiple features per day provide the best improvement over the baseline.