Multi-Element Hierarchical Attention Capsule Network for Stock Prediction

Abstract

Stock prediction is a challenging task concerned by researchers due to its considerable returns. It is difficult because of the high randomness in the stock market. Stock price movement is mainly related to the capital situation and hot events. In recent years, researchers improved prediction accuracy with news and social media. However, the existing methods do not take into account the different influences of events. To solve this problem, we propose a multi-element hierarchical attention capsule network, which consists of two components. The former component, multi-element hierarchical attention, quantifies the importance of valuable information contained in multiple news and social media through its weights assignment process. And the latter component, capsule network, learns more context information from the events through its vector representation in the hidden layer. Moreover, we construct a combined data set to maintain the complementarity between social media and news. Finally, we achieve better results than baselines, and experiments show that our model improves prediction accuracy by quantifying the different influences of events.

Multi-modal Attention Network for Stock Movements Prediction

“…(Feng et al 2019) proposes an adversarial training policy to add perturbations to simulate the stochasticity of price variable. (Liu et al 2020) designed a hierarchical network to fuse both financial news and twitters to enrich the information and achieve higher accuracy. Although making a profound process, these methods lack explicit measures to reduce the chaos in social media and fully utilize multi-modality information.…”

“…(Feng et al 2019) enhance the accuracy of prediction through adversarial training policy. (Liu et al 2019(Liu et al , 2020 resort to attention mechanism and capsule network to mine deeper level of a semantic sequence from social texts.…”

“…Adv-LSTM:(Feng et al 2019) proposes the attentive LSTM model and train it in adversarial training strategy.• StockNet:(Xu and Cohen 2018) proposes a deep generative model which jointly exploiting text and price signals.• MHACN:(Liu et al 2020) first split corpus into news and tweets and then jointly exploit their combined effect. To keep consistent with our dataset, we take textual features and historical trending features as inputs.…”

Order Flow, Technical Analysis And Neural Network: Predicting Short-term Direction Of Futures Contract

“…(2) We ensemble conventional technical analysis features and those generated from high-frequency book depth data ; (3)We apply filters to detect institutional traders from retail traders (4) The modeling of our features involved Purged Group Time Series Split in contrast to traditional cross-validation to prevent target leakages and over-fitting (5)as a result, the accuracy of our model is not state-of-the-art, but the prediction accuracy is relatively consistent across timespan regardless of market condition, which is overlooked in numerous of other works. (6) We can thus produce a high return on selected timespan with a basic trading strategy.…”

Order Flow, Technical Analysis And Neural Network: Predicting Short-term Direction Of Futures Contract

“…Some alternative methods include using news reports and social media are also suggested. Li et al suggest using news sentiment to model the future movements of stocks [6], while [7][8] [9] suggesting using sentiment analysis and language processing to generate predictive features.…”