In the modern capital market, the price of a stock is often considered to be highly volatile and unpredictable because of various social, financial, political and other dynamic factors. With calculated and thoughtful investment, stock market can ensure a handsome profit with minimal capital investment, while incorrect prediction can easily bring catastrophic financial loss to the investors. This paper introduces the application of a recently introduced machine learning model — the transformer model, to predict the future price of stocks of Dhaka Stock Exchange (DSE), the leading stock exchange in Bangladesh. The transformer model has been widely leveraged for natural language processing and computer vision tasks, but, to the best of our knowledge, has never been used for stock price prediction task task using DSE data. Recently, the introduction of time2vec encoding to represent the time series features has made it possible to employ the transformer model for the stock price prediction. This paper aims to leverage these two effective techniques to discover forecasting ability on the volatile stock market of DSE. We deal with the historical daily and weekly data of eight specific stocks listed in DSE. Our experiments demonstrate promising results and acceptable root-mean-squared error on most of the stocks. We also compare the performance of our model with that of a well-known benchmark stock forecasting model called ARIMA and report satisfactory results.

Abstract Learning‐to‐rank (LtR) has become an integral part of modern ranking systems. In this field, the random forest–based rank‐learning algorithms are shown to be among of the top performers. Traditionally, each tree of a random forest is learnt using a bootstrapped copy of the training set, where approximately 63% of the examples are unique. The goal of using a bootstrapped copy instead of the original training set is to reduce the correlation between individual trees, thereby making the prediction of the ensemble more accurate. In this regard, the following question may be raised: how can we leverage the correlation between the trees in favor of performance and scalability of a random forest–based LtR algorithm? In this article, we investigate whether we can further decrease the correlation between the trees while maintaining or possibly improving accuracy. Among several potential options to achieve this goal, we investigate the size of the subsamples used for learning individual trees. We examine the performance of a random forest–based LtR algorithm as we control the correlation using this parameter. Experiments on LtR data sets reveal that for small‐ to moderate‐sized data sets, substantial reduction in training time can be achieved using only a small amount of training data per tree. Moreover, due to the positive correlation between the variability across the trees and performance of a random forest, we observe an increase in accuracy while maintaining the same level of model stability as the baseline. For big data sets, although our experiments did not observe an increase in accuracy (because, with larger data sets, the individual tree variance is already comparatively smaller), our technique is still applicable as it allows for greater scalability.

Current random-forest (RF)-based learning-to-rank (LtR) algorithms use a classification or regression framework to solve the ranking problem in a pointwise manner. The success of this simple yet effective approach coupled with the inherent parallelizability of the learning algorithm makes it a strong candidate for widespread adoption. In this article, we aim to better understand the effectiveness of RF-based rank-learning algorithms with a focus on the comparison between pointwise and listwise approaches. We introduce what we believe to be the first listwise version of an RF-based LtR algorithm. The algorithm directly optimizes an information retrieval metric of choice (in our case, NDCG) in a greedy manner. Direct optimization of the listwise objective functions is computationally prohibitive for most learning algorithms, but possible in RF since each tree maximizes the objective in a coordinate-wise fashion. Computational complexity of the listwise approach is higher than the pointwise counterpart; hence for larger datasets, we design a hybrid algorithm that combines a listwise objective in the early stages of tree construction and a pointwise objective in the latter stages. We also study the effect of the discount function of NDCG on the listwise algorithm. Experimental results on several publicly available LtR datasets reveal that the listwise/hybrid algorithm outperforms the pointwise approach on the majority (but not all) of the datasets. We then investigate several aspects of the two algorithms to better understand the inevitable performance tradeoffs. The aspects include examining an RF-based unsupervised LtR algorithm and comparing individual tree strength. Finally, we compare the the investigated RF-based algorithms with several other LtR algorithms.