Equities

Reinforcement Learning with Maskable Stock Representation for Portfolio Management in Customizable Stock Pools ArXiv ID: 2311.10801 “View on arXiv” Authors: Unknown Abstract Portfolio management (PM) is a fundamental financial trading task, which explores the optimal periodical reallocation of capitals into different stocks to pursue long-term profits. Reinforcement learning (RL) has recently shown its potential to train profitable agents for PM through interacting with financial markets. However, existing work mostly focuses on fixed stock pools, which is inconsistent with investors’ practical demand. Specifically, the target stock pool of different investors varies dramatically due to their discrepancy on market states and individual investors may temporally adjust stocks they desire to trade (e.g., adding one popular stocks), which lead to customizable stock pools (CSPs). Existing RL methods require to retrain RL agents even with a tiny change of the stock pool, which leads to high computational cost and unstable performance. To tackle this challenge, we propose EarnMore, a rEinforcement leARNing framework with Maskable stOck REpresentation to handle PM with CSPs through one-shot training in a global stock pool (GSP). Specifically, we first introduce a mechanism to mask out the representation of the stocks outside the target pool. Second, we learn meaningful stock representations through a self-supervised masking and reconstruction process. Third, a re-weighting mechanism is designed to make the portfolio concentrate on favorable stocks and neglect the stocks outside the target pool. Through extensive experiments on 8 subset stock pools of the US stock market, we demonstrate that EarnMore significantly outperforms 14 state-of-the-art baselines in terms of 6 popular financial metrics with over 40% improvement on profit. ...

Predicting risk/reward ratio in financial markets for asset management using machine learning ArXiv ID: 2311.09148 “View on arXiv” Authors: Unknown Abstract Financial market forecasting remains a formidable challenge despite the surge in computational capabilities and machine learning advancements. While numerous studies have underscored the precision of computer-generated market predictions, many of these forecasts fail to yield profitable trading outcomes. This discrepancy often arises from the unpredictable nature of profit and loss ratios in the event of successful and unsuccessful predictions. In this study, we introduce a novel algorithm specifically designed for forecasting the profit and loss outcomes of trading activities. This is further augmented by an innovative approach for integrating these forecasts with previous predictions of market trends. This approach is designed for algorithmic trading, enabling traders to assess the profitability of each trade and calibrate the optimal trade size. Our findings indicate that this method significantly improves the performance of traditional trading strategies as well as algorithmic trading systems, offering a promising avenue for enhancing trading decisions. ...

Application Research of Spline Interpolation and ARIMA in the Field of Stock Market Forecasting ArXiv ID: 2311.10759 “View on arXiv” Authors: Unknown Abstract The ARIMA (Autoregressive Integrated Moving Average model) has extensive applications in the field of time series forecasting. However, the predictive performance of the ARIMA model is limited when dealing with data gaps or significant noise. Based on previous research, we have found that cubic spline interpolation performs well in capturing the smooth changes of stock price curves, especially when the market trends are relatively stable. Therefore, this paper integrates the two approaches by taking the time series data in stock trading as an example, establishes a time series forecasting model based on cubic spline interpolation and ARIMA. Through validation, the model has demonstrated certain guidance and reference value for short-term time series forecasting. ...

Portfolio diversification with varying investor abilities ArXiv ID: 2311.06519 “View on arXiv” Authors: Unknown Abstract We introduce new mathematical methods to study the optimal portfolio size of investment portfolios over time, considering investors with varying skill levels. First, we explore the benefit of portfolio diversification on an annual basis for poor, average and strong investors defined by the 10th, 50th and 90th percentiles of risk-adjusted returns, respectively. Second, we conduct a thorough regression experiment examining quantiles of risk-adjusted returns as a function of portfolio size across investor ability, testing for trends and curvature within these functions. Finally, we study the optimal portfolio size for poor, average and strong investors in a continuously temporal manner using more than 20 years of data. We show that strong investors should hold concentrated portfolios, poor investors should hold diversified portfolios; average investors have a less obvious distribution with the optimal number varying materially over time. ...

Benchmark Beating with the Increasing Convex Order ArXiv ID: 2311.01692 “View on arXiv” Authors: Unknown Abstract In this paper we model benchmark beating with the increasing convex order (ICX order). The mean constraint in the mean-variance theory of portfolio selection can be regarded as beating a constant. We then investigate the problem of minimizing the variance of a portfolio with ICX order constraints, based on which we also study the problem of beating-performance-variance efficient portfolios. The optimal and efficient portfolios are all worked out in closed form for complete markets. ...

Robust Estimation of Realized Correlation: New Insight about Intraday Fluctuations in Market Betas ArXiv ID: 2310.19992 “View on arXiv” Authors: Unknown Abstract Time-varying volatility is an inherent feature of most economic time-series, which causes standard correlation estimators to be inconsistent. The quadrant correlation estimator is consistent but very inefficient. We propose a novel subsampled quadrant estimator that improves efficiency while preserving consistency and robustness. This estimator is particularly well-suited for high-frequency financial data and we apply it to a large panel of US stocks. Our empirical analysis sheds new light on intra-day fluctuations in market betas by decomposing them into time-varying correlations and relative volatility changes. Our results show that intraday variation in betas is primarily driven by intraday variation in correlations. ...

Potential of ChatGPT in predicting stock market trends based on Twitter Sentiment Analysis ArXiv ID: 2311.06273 “View on arXiv” Authors: Unknown Abstract The rise of ChatGPT has brought a notable shift to the AI sector, with its exceptional conversational skills and deep grasp of language. Recognizing its value across different areas, our study investigates ChatGPT’s capacity to predict stock market movements using only social media tweets and sentiment analysis. We aim to see if ChatGPT can tap into the vast sentiment data on platforms like Twitter to offer insightful predictions about stock trends. We focus on determining if a tweet has a positive, negative, or neutral effect on two big tech giants Microsoft and Google’s stock value. Our findings highlight a positive link between ChatGPT’s evaluations and the following days stock results for both tech companies. This research enriches our view on ChatGPT’s adaptability and emphasizes the growing importance of AI in shaping financial market forecasts. ...

Uncovering Market Disorder and Liquidity Trends Detection ArXiv ID: 2310.09273 “View on arXiv” Authors: Unknown Abstract The primary objective of this paper is to conceive and develop a new methodology to detect notable changes in liquidity within an order-driven market. We study a market liquidity model which allows us to dynamically quantify the level of liquidity of a traded asset using its limit order book data. The proposed metric holds potential for enhancing the aggressiveness of optimal execution algorithms, minimizing market impact and transaction costs, and serving as a reliable indicator of market liquidity for market makers. As part of our approach, we employ Marked Hawkes processes to model trades-through which constitute our liquidity proxy. Subsequently, our focus lies in accurately identifying the moment when a significant increase or decrease in its intensity takes place. We consider the minimax quickest detection problem of unobservable changes in the intensity of a doubly-stochastic Poisson process. The goal is to develop a stopping rule that minimizes the robust Lorden criterion, measured in terms of the number of events until detection, for both worst-case delay and false alarm constraint. We prove our procedure’s optimality in the case of a Cox process with simultaneous jumps, while considering a finite time horizon. Finally, this novel approach is empirically validated by means of real market data analyses. ...

Statistical arbitrage portfolio construction based on preference relations ArXiv ID: 2310.08284 “View on arXiv” Authors: Unknown Abstract Statistical arbitrage methods identify mispricings in securities with the goal of building portfolios which are weakly correlated with the market. In pairs trading, an arbitrage opportunity is identified by observing relative price movements between a pair of two securities. By simultaneously observing multiple pairs, one can exploit different arbitrage opportunities and increase the performance of such methods. However, the use of a large number of pairs is difficult due to the increased probability of contradictory trade signals among different pairs. In this paper, we propose a novel portfolio construction method based on preference relation graphs, which can reconcile contradictory pairs trading signals across multiple security pairs. The proposed approach enables joint exploitation of arbitrage opportunities among a large number of securities. Experimental results using three decades of historical returns of roughly 500 stocks from the S&P 500 index show that the portfolios based on preference relations exhibit robust returns even with high transaction costs, and that their performance improves with the number of securities considered. ...

Quantum-Enhanced Forecasting: Leveraging Quantum Gramian Angular Field and CNNs for Stock Return Predictions ArXiv ID: 2310.07427 “View on arXiv” Authors: Unknown Abstract We propose a time series forecasting method named Quantum Gramian Angular Field (QGAF). This approach merges the advantages of quantum computing technology with deep learning, aiming to enhance the precision of time series classification and forecasting. We successfully transformed stock return time series data into two-dimensional images suitable for Convolutional Neural Network (CNN) training by designing specific quantum circuits. Distinct from the classical Gramian Angular Field (GAF) approach, QGAF’s uniqueness lies in eliminating the need for data normalization and inverse cosine calculations, simplifying the transformation process from time series data to two-dimensional images. To validate the effectiveness of this method, we conducted experiments on datasets from three major stock markets: the China A-share market, the Hong Kong stock market, and the US stock market. Experimental results revealed that compared to the classical GAF method, the QGAF approach significantly improved time series prediction accuracy, reducing prediction errors by an average of 25% for Mean Absolute Error (MAE) and 48% for Mean Squared Error (MSE). This research confirms the potential and promising prospects of integrating quantum computing with deep learning techniques in financial time series forecasting. ...