Abstract-Financial time series forecasting is a popular application of machine learning methods. Previous studies report that advanced forecasting methods predict price changes in financial markets with high accuracy and that profit can be made trading on these predictions.However, financial economists point to the informational efficiency of financial markets, which questions price predictability and opportunities for profitable trading. The objective of the paper is to resolve this contradiction. To this end, we undertake an extensive forecasting simulation, based on data from thirty-four financial indices over six years. These simulations confirm that the best machine learning methods produce more accurate forecasts than the best econometric methods. We also examine the methodological factors that impact the predictive accuracy of machine learning forecasting experiments. The results suggest that the predictability of a financial market and the feasibility of profitable model-based trading are significantly influenced by the maturity of the market, the forecasting method employed, the horizon for which it generates predictions and the methodology used to assess the model and simulate model-based trading. We also find evidence against the informational value of indicators from the field of technical analysis. Overall, we confirm that advanced forecasting methods can be used to predict price changes in some financial markets and we discuss whether these results question the prevailing view in the financial economics literature that financial markets are efficient.

The paper examines the potential of deep learning to support decisions in financial risk management.We develop a deep learning model for predicting whether individual spread traders secure profits from future trades. This task embodies typical modeling challenges faced in risk and behavior forecasting.Conventional machine learning requires data that is representative of the feature-target relationship and relies on the often costly development, maintenance, and revision of handcrafted features. Consequently, modeling highly variable, heterogeneous patterns such as trader behavior is challenging. Deep learning promises a remedy. Learning hierarchical distributed representations of the data in an automatic manner (e.g. risk taking behavior), it uncovers generative features that determine the target (e.g., trader's profitability), avoids manual feature engineering, and is more robust toward change (e.g. dynamic market conditions). The results of employing a deep network for operational risk forecasting confirm the feature learning capability of deep learning, provide guidance on designing a suitable network architecture and demonstrate the superiority of deep learning over machine learning and rule-based benchmarks.

No abstract

Many existing learning algorithms suffer from limited architectural depth and the locality of estimators, making it difficult to generalize from the test set and providing inefficient and biased estimators. Deep architectures have been shown to appropriately learn correlation structures in time series data. This paper compares the effectiveness of a deep feedforward Neural Network (DNN) and shallow architectures (e.g., Support Vector Machine (SVM) and one-layer NN) when predicting a broad crosssection of stock price indices in both developed and emerging markets. An extensive evaluation is undertaken, using daily, hourly, minute and tick level data related to thirty-four financial indices from 32 countries across six years. Our evaluation results show a considerable advantage from training deep (cf. shallow) architectures, using a rectifier linear (RELU) activation function, across all thirty-four markets when 'minute' data is used. However, the predictive performance of DNN was not significantly better than that of shallower architectures when using tick level data. This result suggests that when training a DNN algorithm, the predictive accuracy peaks, regardless of training size. We also examine which activation function works best for stock price index data. Our results demonstrate that the RELU activation function performs better than TANH across all markets and time horizons when using DNN to predict stock price indices.

A network with n nodes contains O(n 2) possible links. Even for networks of modest size, it is often difficult to evaluate all pairwise possibilities for links in a meaningful way. Further, even though link prediction is closely related to missing value estimation problems, it is often difficult to use sophisticated models such as latent factor methods because of their computational complexity on large networks. Hence, most known link prediction methods are designed for evaluating the link propensity on a specified subset of links, rather than on the entire networks. In practice, however, it is essential to perform an exhaustive search over the entire networks. In this article, we propose an ensemble enabled approach to scaling up link prediction, by decomposing traditional link prediction problems into subproblems of smaller size. These subproblems are each solved with latent factor models, which can be effectively implemented on networks of modest size. By incorporating with the characteristics of link prediction, the ensemble approach further reduces the sizes of subproblems without sacrificing its prediction accuracy. The ensemble enabled approach has several advantages in terms of performance, and our experimental results demonstrate the effectiveness and scalability of our approach.