Search

Research into algorithmic trading using reinforcement learning has been garnering increasing popularity in recent years. While most research work focuses on solving a certain modelling problem or data problem with positive results, we believe that in an application as critical as financial trading, aligning the machine to human behaviours is imperative and should be regarded as the basis of all further improvements before machine algorithms are free to go their own innovative ways. In this paper, we are proposing a trading model whose design principles are based on bringing a machine trading agent close to a human trader. We study areas where human alignment is necessary and introduce as a solution a novel multi-loss function of the model combining supervised learning, single-step and multi-step Q learning, and also inject the paradigm of imitation learning in the training and trading processes. We also introduce a realistic backtesting setup and a holding position-aware profit calculation scheme under which the machine algorithm conducts intra-day trading using minute tick data over a group of U. S. stocks chosen to represent different industrial sectors and liquidity levels. Our model's overall out-performance over a group of baseline models as well as our ablation study results justify the inclusion of individual model features all of which are introduced to bring aspects of the model behaviour more aligned with those of a human trader. • Essential to align trading algorithm with behaviour of a human trader. • Introduce an imitative multi-loss DQN to achieve behavioural alignment. • Introduce a realistic backtesting and trading profit calculation scheme. • Tested using minute tick data of selected US stocks under different scenarios. • Tested against selected baseline models as well as buy-to-hold. [ABSTRACT FROM AUTHOR]

• Predict cumulative abnormal return of stocks following earnings release using XGBoost. • Study drivers of post-earnings-release drift (PEAD) as identified by XGBoost. • Remedy the difficulty of buying into a moving market when trading on PEAD signals. Post-Earnings-Announcement Drift (PEAD) is a stock market phenomenon when a stock's cumulative abnormal return has a tendency to drift in the direction of an earnings surprise in the near term following an earnings announcement. Although it is one of the most studied stock market anomalies, the current literature is often limited in explaining this phenomenon by a small number of factors using simpler regression methods. In this paper, we use a machine learning based approach instead, and aim to capture the PEAD dynamics using data from a large group of stocks and a wide range of both fundamental and technical factors. Our model is built around the Extreme Gradient Boosting (XGBoost) and uses a long list of engineered input features based on quarterly financial announcement data from 1,106 companies in the Russell 1000 index between 1997 and 2018. We perform numerous experiments on PEAD predictions and analysis and have the following contributions to the literature. First, we show how Post-Earnings-Announcement Drift can be analysed using machine learning methods and demonstrate such methods' prowess in credibly forecasting the drift direction. It is the first time PEAD dynamics are studied using XGBoost. We show that the drift direction is driven by different factors for stocks from different industrial sectors and in different quarters and XGBoost is effective in understanding the changing dynamics. Second, we show that an XGBoost well optimised by a Genetic Algorithm can help allocate out-of-sample stocks to form portfolios with higher positive returns to long and portfolios with lower negative returns to short, a finding that could be adopted in the process of developing market neutral strategies. Third, we show how theoretical event-driven stock strategies have to grapple with ever-changing market prices in reality, reducing their effectiveness. We present a tactic to remedy the difficulty of buying into a moving market when trading on PEAD signals. [ABSTRACT FROM AUTHOR]

Abstract A series of BaLaMgSb 1- x Nb x O 6 :Eu3+ double perovskite red phosphors was successfully obtained. X-ray diffraction ans Rietveld refinement analyses were conducted to determine the phase information and the detailed structure parameters. The coordinate variations of both La3+/Eu3+ and Sb5+/Nb5+ were discussed to elucidate the influence of B-site ion doping on the lattice variation. Luminescence properties, excitation and emission spectra, were presented to show the advantages of doping with Nb5+ ion. Ultraviolet-vis diffuse reflectance spectra were performed to reveal the reason for the decreased emission intensity under the charge transfer band excitation. Moreover, band gap energy was estimated to clarify the relationship between the increased intensity (λex = 395 and 465 nm) and Nb5+ concentration. Intensity ratios of I(615)/I(590) were performed to show the symmetry variation of the lattice. Thermal quenching property was also investigated and the quenching mechanism was discussed in detail based on the ionization process. [ABSTRACT FROM AUTHOR]