Showing papers on "Algorithmic trading published in 2019"

Improving financial trading decisions using deep Q-learning: Predicting the number of shares, action strategies, and transfer learning

Abstract: We study trading systems using reinforcement learning with three newly proposed methods to maximize total profits and reflect real financial market situations while overcoming the limitations of financial data. First, we propose a trading system that can predict the number of shares to trade. Specifically, we design an automated system that predicts the number of shares by adding a deep neural network (DNN) regressor to a deep Q-network, thereby combining reinforcement learning and a DNN. Second, we study various action strategies that use Q-values to analyze which action strategies are beneficial for profits in a confused market. Finally, we propose transfer learning approaches to prevent overfitting from insufficient financial data. We use four different stock indices—the S&P500, KOSPI, HSI, and EuroStoxx50—to experimentally verify our proposed methods and then conduct extensive research. The proposed automated trading system, which enables us to predict the number of shares with the DNN regressor, increases total profits by four times in S&P500, five times in KOSPI, 12 times in HSI, and six times in EuroStoxx50 compared with the fixed-number trading system. When the market situation is confused, delaying the decision to buy or sell increases total profits by 18% in S&P500, 24% in KOSPI, and 49% in EuroStoxx50. Further, transfer learning increases total profits by twofold in S&P500, 3 times in KOSPI, twofold in HSI, and 2.5 times in EuroStoxx50. The trading system with all three proposed methods increases total profits by 13 times in S&P500, 24 times in KOSPI, 30 times in HSI, and 18 times in EuroStoxx50, outperforming the market and the reinforcement learning model.

Automated trading systems statistical and machine learning methods and hardware implementation: a survey

Abstract: Automated trading, which is also known as algorithmic trading, is a method of using a predesigned computer program to submit a large number of trading orders to an exchange. It is substantially a r ...

Deep Robust Reinforcement Learning for Practical Algorithmic Trading

Abstract: In algorithmic trading, feature extraction and trading strategy design are two prominent challenges to acquire long-term profits. However, the previously proposed methods rely heavily on domain knowledge to extract handcrafted features and lack an effective way to dynamically adjust the trading strategy. With the recent breakthroughs of deep reinforcement learning (DRL), sequential real-world problems can be modeled and solved with a more human-like approach. In this paper, we propose a novel trading agent, based on deep reinforcement learning, to autonomously make trading decisions and gain profits in the dynamic financial markets. We extend the value-based deep Q-network (DQN) and the asynchronous advantage actor-critic (A3C) for better adapting to the trading market. Specifically, in order to automatically extract robust market representations and resolve the financial time series dependence, we utilize the stacked denoising autoencoders (SDAEs) and the long short-term memory (LSTM) as parts of the function approximator, respectively. Furthermore, we design several elaborate mechanisms to make the trading agent more practical to the real trading environment, such as position-controlled action and n-step reward. The experimental results show that our trading agent outperforms the baselines and achieves stable risk-adjusted returns in both the stock and the futures markets.

DeepClue: Visual Interpretation of Text-Based Deep Stock Prediction

Abstract: The recent advance of deep learning has enabled trading algorithms to predict stock price movements more accurately. Unfortunately, there is a significant gap in the real-world deployment of this breakthrough. For example, professional traders in their long-term careers have accumulated numerous trading rules, the myth of which they can understand quite well. On the other hand, deep learning models have been hardly interpretable. This paper presents DeepClue, a system built to bridge text-based deep learning models and end users through visually interpreting the key factors learned in the stock price prediction model. We make three contributions in DeepClue. First, by designing the deep neural network architecture for interpretation and applying an algorithm to extract relevant predictive factors, we provide a useful case on what can be interpreted out of the prediction model for end users. Second, by exploring hierarchies over the extracted factors and displaying these factors in an interactive, hierarchical visualization interface, we shed light on how to effectively communicate the interpreted model to end users. Specially, the interpretation separates the predictables from the unpredictables for stock prediction through the use of intercept model parameters and a risk visualization design. Third, we evaluate the integrated visualization system through two case studies in predicting the stock price with financial news and company-related tweets from social media. Quantitative experiments comparing the proposed neural network architecture with state-of-the-art models and the human baseline are conducted and reported. Feedbacks from an informal user study with domain experts are summarized and discussed in details. The study results demonstrate the effectiveness of DeepClue in helping to complete stock market investment and analysis tasks.

How Algorithms Interact: Goffman's 'Interaction Order' in Automated Trading

Abstract: In a talk in 2013, Karin Knorr Cetina referred to ‘the interaction order of algorithms’, a phrase that implicitly invokes Erving Goffman's ‘interaction order’. This paper explores the application o...

ABIDES: Towards High-Fidelity Market Simulation for AI Research.

Abstract: We introduce ABIDES, an Agent-Based Interactive Discrete Event Simulation environment. ABIDES is designed from the ground up to support AI agent research in market applications. While simulations are certainly available within trading firms for their own internal use, there are no broadly available high-fidelity market simulation environments. We hope that the availability of such a platform will facilitate AI research in this important area. ABIDES currently enables the simulation of tens of thousands of trading agents interacting with an exchange agent to facilitate transactions. It supports configurable pairwise network latencies between each individual agent as well as the exchange. Our simulator's message-based design is modeled after NASDAQ's published equity trading protocols ITCH and OUCH. We introduce the design of the simulator and illustrate its use and configuration with sample code, validating the environment with example trading scenarios. The utility of ABIDES is illustrated through experiments to develop a market impact model. We close with discussion of future experimental problems it can be used to explore, such as the development of ML-based trading algorithms.

A Novel Hybrid Model for Stock Price Forecasting Based on Metaheuristics and Support Vector Machine

Abstract: This paper intends to present a new model for the accurate forecast of the stock’s future price. Stock price forecasting is one of the most complicated issues in view of the high fluctuation of the stock exchange and also it is a key issue for traders and investors. Many predicting models were upgraded by academy investigators to predict stock price. Despite this, after reviewing the past research, there are several negative aspects in the previous approaches, namely: (1) stringent statistical hypotheses are essential; (2) human interventions take part in predicting process; and (3) an appropriate range is complex to be discovered. Due to the problems mentioned, we plan to provide a new integrated approach based on Artificial Bee Colony (ABC), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Support Vector Machine (SVM). ABC is employed to optimize the technical indicators for forecasting instruments. To achieve a more precise approach, ANFIS has been applied to predict long-run price fluctuations of the stocks. SVM was applied to create the nexus between the stock price and technical indicator and to further decrease the forecasting errors of the presented model, whose performance is examined by five criteria. The comparative outcomes, obtained by running on datasets taken from 50 largest companies of the U.S. Stock Exchange from 2008 to 2018, have clearly demonstrated that the suggested approach outperforms the other methods in accuracy and quality. The findings proved that our model is a successful instrument in stock price forecasting and will assist traders and investors to identify stock price trends, as well as it is an innovation in algorithmic trading.

Mean-Field Game Strategies for Optimal Execution

Abstract: Algorithmic trading strategies for execution often focus on the individual agent who is liquidating/acquiring shares. When generalized to multiple agents, the resulting stochastic game is notorious...

High frequency trading strategies, market fragility and price spikes: an agent based model perspective

Abstract: Given recent requirements for ensuring the robustness of algorithmic trading strategies laid out in the Markets in Financial Instruments Directive II, this paper proposes a novel agent-based simulation for exploring algorithmic trading strategies. Five different types of agents are present in the market. The statistical properties of the simulated market are compared with equity market depth data from the Chi-X exchange and found to be significantly similar. The model is able to reproduce a number of stylised market properties including: clustered volatility, autocorrelation of returns, long memory in order flow, concave price impact and the presence of extreme price events. The results are found to be insensitive to reasonable parameter variations.

Daily Market News Sentiment and Stock Prices

Abstract: In recent years there has been a tremendous growth in the influx of news related to traded assets in international financial markets. This financial news is now available via print media but also through real-time online sources such as internet news and social media sources. The increase in the availability of financial news and investor’s ease of access to it has a potentially significant impact on market price formation as these news items are swiftly transformed into investors sentiment which in turn drives prices. Various commercial agencies have started developing their own financial news data sets which are used by investors and traders to support their algorithmic trading strategies. Thomson Reuters News Analytics (TRNA)1 is one such data set. In this study we use the TRNA data set to construct a series of daily sentiment scores for Dow Jones Industrial Average (DJIA) stock index component companies. We use these daily DJIA market sentiment scores to study the influence of financial news sentiment scores on the stock prices of these companies using a multi-factor model. We use an augmented Fama French Three Factor Model to evaluate the additional effects of financial news sentiment on stock prices in the context of this model. Our results suggest that even when market factors are taken into account, sentiment scores have a significant effect on Dow Jones constituent company returns and that lagged daily sentiment scores are often significant, suggesting that information compounded in these scores is not immediately reflected in security prices and related return series.

Grid trading system robot (GTSbot): A novel mathematical algorithm for trading FX market

Abstract: Grid algorithmic trading has become quite popular among traders because it shows several advantages with respect to similar approaches. Basically, a grid trading strategy is a method that seeks to make profit on the market movements of the underlying financial instrument by positioning buy and sell orders properly time-spaced (grid distance). The main advantage of the grid trading strategy is the financial sustainability of the algorithm because it provides a robust way to mediate losses in financial transactions even though this also means very complicated trades management algorithm. For these reasons, grid trading is certainly one of the best approaches to be used in high frequency trading (HFT) strategies. Due to the high level of unpredictability of the financial markets, many investment funds and institutional traders are opting for the HFT (high frequency trading) systems, which allow them to obtain high performance due to the large number of financial transactions executed in the short-term timeframe. The combination of HFT strategies with the use of machine learning methods for the financial time series forecast, has significantly improved the capability and overall performance of the modern automated trading systems. Taking this into account, the authors propose an automatic HFT grid trading system that operates in the FOREX (foreign exchange) market. The performance of the proposed algorithm together with the reduced drawdown confirmed the effectiveness and robustness of the proposed approach.

Trading co‐integrated assets with price impact

Abstract: Executing a basket of co-integrated assets is an important task facing investors. Here, we show how to do this accounting for the informational advantage gained from assets within and outside the basket, as well as for the permanent price impact of market orders (MOs) from all market participants, and the temporary impact that the agent's MOs have on prices. The execution problem is posed as an optimal stochastic control problem and we demonstrate that, under some mild conditions, the value function admits a closed-form solution, and prove a verification theorem. Furthermore, we use data of five stocks traded in the Nasdaq exchange to estimate the model parameters and use simulations to illustrate the performance of the strategy. As an example, the agent liquidates a portfolio consisting of shares in Intel Corporation (INTC) and Market Vectors Semiconductor ETF (SMH). We show that including the information provided by three additional assets, FARO Technologies (FARO), NetApp (NTAP) and Oracle Corporation (ORCL), considerably improves the strategy's performance; for the portfolio we execute, it outperforms the multi-asset version of Almgren-Chriss by approximately 4 to 4.5 basis points.

A Machine Learning Framework for Algorithmic Trading with Virtual Bids in Electricity Markets

Abstract: This paper develops a machine learning framework for algorithmic trading with virtual bids in electricity markets. In the proposed algorithmic trading strategy, a budget and risk constrained portfolio optimization problem is solved, which selects the virtual transactions to be executed. In order to maximize the expected net earnings of the virtual bid portfolio, a mixture density network model is developed to provide robust and accurate forecasts for electricity price spread between day-ahead and real-time market. By leveraging a coherent risk measure and historical price samples, the risk-constrained portfolio optimization problem is solved efficiently. Backcasting results based on market data from ISO New England show that our proposed mixture density network based trading strategy consistently outperforms the benchmark online learning approach.

Increasing the Tick: Examining the Impact of the Tick Size Change on Maker-Taker and Taker-Maker Market Models

Abstract: We investigate the effects of an increase in tick size on order and trading flow across market fee models. Using the pilot firms in the U.S. Securities and Exchange Commission's Tick Size Pilot Program, we document that trade and order volume declines on maker‐taker fee models after the tick size implementation. We find that the inverted fee models (taker‐maker) experience an increase in both trade and order volume. Additionally, we find that a tick size adjustment has a substantial influence on market participation in maker‐taker fee models. We also find that measures of both hidden and algorithmic trading decline with an increasing tick size, which is strongly moderated by the differences in the maker‐taker and taker‐maker fee models.

Trading algorithms with learning in latent alpha models

Abstract: Alpha signals for statistical arbitrage strategies are often driven by latent factors. This paper analyses how to optimally trade with latent factors that cause prices to jump and diffuse. Moreover, we account for the effect of the trader's actions on quoted prices and the prices they receive from trading. Under fairly general assumptions, we demonstrate how the trader can learn the posterior distribution over the latent states, and explicitly solve the latent optimal trading problem. We provide a verification theorem, and a methodology for calibrating the model by deriving a variation of the expectation-maximization algorithm. To illustrate the efficacy of the optimal strategy, we demonstrate its performance through simulations and compare it to strategies which ignore learning in the latent factors. We also provide calibration results for a particular model using Intel Corporation stock as an example.

Adaptive-Aggressive Traders Don’t Dominate

Abstract: For more than a decade Vytelingum’s Adaptive-Aggressive (AA) algorithm has been recognized as the best-performing automated auction-market trading-agent strategy currently known in the AI/Agents literature; in this paper, we demonstrate that it is in fact routinely outperformed by another algorithm when exhaustively tested across a sufficiently wide range of market scenarios. The novel step taken here is to use large-scale compute facilities to brute-force exhaustively evaluate AA in a variety of market environments based on those used for testing it in the original publications. Our results show that even in these simple environments AA is consistently outperformed by IBM’s GDX algorithm, first published in 2002. We summarize here results from more than one million market simulation experiments, orders of magnitude more testing than was reported in the original publications that first introduced AA. A 2019 ICAART paper by Cliff claimed that AA’s failings were revealed by testing it in more realistic experiments, with conditions closer to those found in real financial markets, but here we demonstrate that even in the simple experiment conditions that were used in the original AA papers, exhaustive testing shows AA to be outperformed by GDX. We close this paper with a discussion of the methodological implications of our work: any results from previous papers where any one trading algorithm is claimed to be superior to others on the basis of only a few thousand trials are probably best treated with some suspicion now. The rise of cloud computing means that the compute-power necessary to subject trading algorithms to millions of trials over a wide range of conditions is readily available at reasonable cost: we should make use of this; exhaustive testing such as is shown here should be the norm in future evaluations and comparisons of new trading algorithms.

Algorithmic and high frequency trading in Asia-Pacific, now and the future

Abstract: The Asia-Pacific securities markets are among the fastest growing markets in the world and account for more than one third of the global market capitalization. Drawing from the literature and recent technological developments worldwide, we discuss the current state and the future developments of computerized trading in a set of the largest Asia-Pacific economies, which constitute approximately 85% of the region's securities market. We first identify the drivers and deterrents of computerized trading based on the academic literature and regulatory investigations. We then assess the current viability and the future growth of computerized trading in the Asia-Pacific economies. Finally, we survey the empirical findings on algorithmic and high frequency trading in the Asia-Pacific region in comparison with the global empirical and theoretical literature.

Using Reinforcement Learning in the Algorithmic Trading Problem

Abstract: —The development of reinforced learning methods has extended application to many areas including algorithmic trading. In this paper trading on the stock exchange is interpreted into a game with a Markov property consisting of states, actions, and rewards. A system for trading the fixed volume of a financial instrument is proposed and experimentally tested; this is based on the asynchronous advantage actor-critic method with the use of several neural network architectures. The application of recurrent layers in this approach is investigated. The experiments were performed on real anonymized data. The best architecture demonstrated a trading strategy for the RTS Index futures (MOEX:RTSI) with a profitability of 66% per annum accounting for commission. The project source code is available via the following link: http://github.com/evgps/a3c_trading.

Financial Trading Model with Stock Bar Chart Image Time Series with Deep Convolutional Neural Networks

Abstract: Even though computational intelligence techniques have been extensively utilized in financial trading systems, almost all developed models use the time series data for price prediction or identifying buy-sell points. However, in this study we decided to use 2-D stock bar chart images directly without introducing any additional time series associated with the underlying stock. We propose a novel algorithmic trading model CNN-BI (Convolutional Neural Network with Bar Images) using a 2-D Convolutional Neural Network. We generated 2-D images of sliding windows of 30-day bar charts for Dow 30 stocks and trained a deep Convolutional Neural Network (CNN) model for our algorithmic trading model. We tested our model separately between 2007-2012 and 2012-2017 for representing different market conditions. The results indicate that the model was able to outperform Buy and Hold strategy, especially in trendless or bear markets. Since this is a preliminary study and probably one of the first attempts using such an unconventional approach, there is always potential for improvement. Overall, the results are promising and the model might be integrated as part of an ensemble trading model combined with different strategies.

Buying on Margin and Short Selling in an Artificial Double Auction Market

Abstract: Leverage trading, which consists of short selling and buying on margin, has been introduced into stock markets in many countries, including China. Ever since, there have been heated debates on how leverage trading influences financial markets. In this paper, an agent-based artificial market model is developed to simulate market behaviors and to analyze the influence of the leverage ratio on liquidity, volatility and price-discovery efficiency. In our artificial market, heterogeneous agents submit limit orders based on the fundamentalist or chartist strategy, and their effective supplies and demands can be increased by short selling or margin trading. Numerical analyses are performed in both one-sided and two-sided markets. We find that in one-sided markets, leverage trading can increase market liquidity and volatility, and decrease price-discovery efficiency. However, in the two-sided market, the increase of liquidity is much smaller, the volatility is decreased, and the price-discovery efficiency is improved. Generally, this model provides some meaningful results, which are supported by many other studies, and these findings underscore the necessity of building up a two-sided market when introducing leverage trading into stock markets.

Exhaustive Testing of Trader-agents in Realistically Dynamic Continuous Double Auction Markets: AA Does Not Dominate

Abstract: We analyse results from over 3.4million detailed market-trading simulation sessions which collectively confirm an unexpected result: in markets with dynamically varying supply and demand, the best-performing automated adaptive auction-market trading-agent currently known in the AI/Agents literature, i.e. Vytelingum’s Adaptive-Aggressive (AA) strategy, can be routinely out-performed by simpler trading strategies. AA is the most recent in a series of AI trading-agent strategies proposed by various researchers over the past twenty years: research papers contributing major steps in this evolution of strategies have been published at IJCAI, in the Artificial Intelligence journal, and at AAMAS. The innovative step taken here is to brute-force exhaustively evaluate AA in market environments that are in various ways more realistic, closer to real-world financial markets, than the simple constrained abstract experimental evaluations routinely used in the prior academic AI/Agents research literature. We conclude that AA can indeed appear dominant when tested only against other AI-based trading agents in the highly simplified market scenarios that have become the methodological norm in the trading-agents academic research literature, but much of that success seems to be because AA was designed with exactly those simplified experimental markets in mind. As soon as we put AA in scenarios closer to real-world markets, modify it to fit those markets accordingly, and exhaustively test it against simpler trading agents, AA’s dominance simply disappears.

Big Data Algorithmic Trading Systems Based on Investors’ Mood

Abstract: Traditional automated trading systems use rules and filters based on Chartism to send orders to the market, aiming to beat the market and obtain positive returns in bullish or bearish contexts. How...

Robust Asset Allocation for Robo-Advisors

Abstract: In the last few years, the financial advisory industry has been impacted by the emergence of digitalization and robo-advisors. This phenomenon affects major financial services, including wealth management, employee savings plans, asset managers, etc. Since the robo-advisory model is in its early stages, we estimate that robo-advisors will help to manage around $1 trillion of assets in 2020 (OECD, 2017). And this trend is not going to stop with future generations, who will live in a technology-driven and social media-based world. In the investment industry, robo-advisors face different challenges: client profiling, customization, asset pooling, liability constraints, etc. In its primary sense, robo-advisory is a term for defining automated portfolio management. This includes automated trading and rebalancing, but also automated portfolio allocation. And this last issue is certainly the most important challenge for robo-advisory over the next five years. Today, in many robo-advisors, asset allocation is rather human-based and very far from being computer-based. The reason is that portfolio optimization is a very difficult task, and can lead to optimized mathematical solutions that are not optimal from a financial point of view (Michaud, 1989). The big challenge for robo-advisors is therefore to be able to optimize and rebalance hundreds of optimal portfolios without human intervention. In this paper, we show that the mean-variance optimization approach is mainly driven by arbitrage factors that are related to the concept of hedging portfolios. This is why regularization and sparsity are necessary to define robust asset allocation. However, this mathematical framework is more complex and requires understanding how norm penalties impacts portfolio optimization. From a numerical point of view, it also requires the implementation of non-traditional algorithms based on ADMM methods.

Forecasting Financial Markets Using High-Frequency Trading Data: Examination with Strongly Typed Genetic Programming

Abstract: Market regulators around the world are still debating whether high-frequency trading (HFT) plays a positive or negative role in market quality. We develop an artificial futures market populated wit...