Dynamic mode decomposition for financial trading strategies

We demonstrate the application of an algorithmic trading strategy based upon the recently developed dynamic mode decomposition on portfolios of financial data. The method is capable of characterizing complex dynamical systems, in this case financial market dynamics, in an equation-free manner by decomposing the state of the system into low-rank terms whose temporal coefficients in time are known. By extracting key temporal coherent structures (portfolios) in its sampling window, it provides a regression to a best fit linear dynamical system, allowing for a predictive assessment of the market dynamics and informing an investment strategy. The data-driven analytics capitalizes on stock market patterns, either real or perceived, to inform buy/sell/hold investment decisions. Critical to the method is an associated learning algorithm that optimizes the sampling and prediction windows of the algorithm by discovering trading hot-spots. The underlying mathematical structure of the algorithms is rooted in methods from nonlinear dynamical systems and shows that the decomposition is an effective mathematical tool for data-driven discovery of market patterns.     

The predictability of security returns with simple technical trading rules

Technical traders base their analysis on the premise that the patterns in market prices are assumed to recur in the future, and thus, these patterns can be used for predictive purposes. This paper uses the daily Dow Jones Industrial Average Index from 1897 to 1988 to examine the linear and nonlinear predictability of stock market returns with simple technical trading rules. The nonlinear specification of returns are modelled by single layer feedforward networks. The results indicate strong evidence of nonlinear predictability in the stock market returns by using the past buy and sell signals of the moving average rules.     

Decision trees unearth return sign predictability in the S&P 500

Technical trading rules and linear regression models are often used by practitioners to find trends in asset returns. However, these models typically neglect interaction terms between the lagged daily directional movements. We propose a decision tree forecasting model that has the flexibility to capture arbitrary interaction patterns. To study the importance of interaction terms, we construct a binary Markov process with a deterministic component that cannot be predicted without interaction terms between the lagged directional movements. We show that some tree based strategies achieve trading performance significant at the 99% confidence level on the S&P 500 over the past 20 years, after adjusting for multiple testing. The best strategy breaks even with the buy-and-hold strategy at 21 bps in transaction costs per round trip. A four-factor regression analysis shows significant intercept, and correlation with the market. The directional predictability is strongest during the bursts of the dotcom bubble, financial crisis, and European debt crisis. The return sign predictability during these periods confirms the necessity of interaction terms to model daily returns.     

Filter Tests In Nasdaq Stocks

This study examines the performance of filter and dual moving-average crossover trading rules applied to Nasdaq stocks. We find that trading rules conditioned on a stock's past price history perform poorly, but those based on past movements in the overall Nasdaq Index tend to earn statistically significant abnormal returns. Since there is a high level of transaction costs in this market, these abnormal returns are generally not economically significant. However, there are indications that pursuing some of these strategies can be worthwhile in carefully selected subsets of stocks.     

Co‐evolved genetic programs for stock market trading

The profitability of trading rules evolved by three different optimised genetic programs, namely a single population genetic program (GP), a co‐operative co‐evolved GP, and a competitive co‐evolved GP is compared. Profitability is determined by trading thirteen listed shares on the Johannesburg Stock Exchange (JSE) over a period of April 2003 to June 2008. An empirical study presented here shows that GPs can generate profitable trading rules across a variety of industries and market conditions. The results show that the co‐operative co‐evolved GP generates trading rules perform significantly worse than a single population GP and a competitively co‐evolved GP. The results also show that a competitive co‐evolved GP and the single population GP produce similar trading rules. The profits returned by the evolved trading rules are compared to the profit returned by the buy‐and‐hold trading strategy. The evolved trading rules significantly outperform the buy‐and‐hold strategy when the market trends downwards. No significant difference is identified among the buy‐and‐hold strategy, the competitive co‐evolved GP, and single population GP when the market trends upwards.     

Stock returns,trading volume,and volatility: The case of African stock markets

The presence of the African Stock Markets (ASMs) in the global frontier markets indices confirms their global portfolio diversification role. This study investigates the asymmetric and intertemporal causality among the stock returns, trading volume, and volatility of eight ASMs. Results based on the linear model reveal that return generally Granger cause trading volume. However, evidence from the quantile regression shows that lagged trading volume has a negative causal effect on returns at low quantiles and positive causal effects at high quantiles. This evidence is consistent with volume-return equilibrium models, disposition and overconfidence models, and information asymmetry models. The positive causal effects of volatility on volume support the dispersion of beliefs model. In contrast, intertemporal evidence of contemporaneous and lagged causal relationships from trading volume to volatility supports the mixture of distribution hypothesis, sequential information acquisition hypothesis, and dynamic efficient market hypothesis. Volume-return and return-volume causality dynamics are quantile-specific and therefore driven by market conditions. However, the volume-volatility causality is dependent on volatility regimes. The linear model results confirm how model misspecification can distort and even reverse empirical evidence relative to nonlinear models.     

An evolutionary multi‐objective optimization of trading rules in call markets

We evaluate an agent‐based model featuring near‐zero‐intelligence traders operating in a call market with a wide range of trading rules governing the determination of prices and which orders are executed, as well as a range of parameters regarding market intervention by market makers and the presence of informed traders. We optimize these trading rules using a multi‐objective population‐based incremental learning algorithm seeking to maximize the trading volume and minimize the bid–ask spread. Our results suggest that markets should choose a small tick size if concerns about the bid–ask spread are dominating and a large tick size if maximizing trading volume is the main aim. We also find that unless concerns about trading volume dominate, time priority is the optimal priority rule. Copyright © 2011 John Wiley & Sons, Ltd.     

Further insights on the puzzle of technical analysis profitability

This paper extends current results concerning technical analysis efficiency on the foreign exchange market and attempts to determine whether filtering the raw exchange rate series with some trading rule significantly changes its characteristics. Because of the non-normality of exchange rate series, bootstrap methods are used on the main daily exchange rates since 1974 to show technical analysis performance. The technical analysis strategy tested generates returns whose distribution is significantly different from the basic series. The robustness of the results is tested in and out-of-sample and an explanation of the technical analysis performance based on its filtering properties is suggested.     

How good can heuristic-based forecasts be? A comparative performance of econometric and heuristic models for UK and US asset returns

This paper systematically investigates the sources of differential out-of-sample predictive accuracy of heuristic frameworks based on internet search frequencies and a large set of econometric models. The volume of internet searches helps gauge the degree of investors’ time-varying interest in specific assets. We use a wide range of state-of-the-art models, both of linear and nonlinear type (regime-switching predictive regressions, threshold autoregressive, smooth transition autoregressive), extended to capture conditional heteroskedasticity through GARCH models. The predictor variables investigated are those typical of the literature featuring a range of macroeconomic and market leading indicators. Our out-of-sample forecasting exercises are conducted with reference to US, UK, French and German data, both stocks and bonds, and for 1- and 12-months-ahead horizons. We employ several forecast performance metrics and predictive accuracy tests. Internet-search-based models are found to perform better than the average of all of the alternative models. For several country-asset-horizon combinations, particularly for UK bond returns, our heuristic models compare favourably with sophisticated econometric methods. The heuristic models are also shown to perform well in forecasting realized volatility. The baseline results are supported by several extensions and robustness checks, such as using alternative search keywords, controlling for Fama–French and Cochrane–Piazzesi factors, and implementing heuristic-based trading strategies.     

Technical trading rules for nonlinear dynamics of stock returns: evidence from the G-7 stock markets

This paper explores a possible link between an asymmetric dynamic process of stock returns and profitable technical trading rules. Using the G-7 stock market indexes, we show that the dynamic process of daily index returns is better characterized by nonlinearity arising from an asymmetric reverting property. The asymmetric reverting property of stock returns is exploitable in generating profitable buy and sells signals for technical trading strategies. The bootstrap analysis shows that not all nonlinearities generate profitable buy and sell signals, but rather only the nonlinearities generating a consistent asymmetrical pattern of return dynamics can be exploitable for the profitability of the trading rules. The significant positive (negative) returns from buy (sell) signals are a consequence of trading rules that exploit the asymmetric nonlinear dynamics of the stock returns that revolve around positive (negative) unconditional mean returns under prior positive (negative) return patterns. Our results corroborate the arguments for the usefulness of technical trading strategies in stock market investments.     

Assessing the relevance of an information source to trading from an adaptive-markets hypothesis perspective

I propose a framework motivated by the Adaptive Markets Hypothesis (AMH) to analyze the relevance of a specific information source for the trading of a given security. To illustrate the applicability and advantages of this methodology, I explore the extent to which the financial statement (FS) is relevant for Credit Default Swap (CDS) trading. Specifically, I adopt a Bayesian Model Averaging approach to examine properties of the accounting metrics that enter the implied trading heuristics of the market participants. Hypothesis-testing is conducted on various horizons around the announcement dates of corporate results. The diversity of trading rules and the shift in the heuristics mix that occurred after 2008 support the AMH perspective. Overall, results show that there is a significant component of profit-motivated trading in the CDS market that relies on financial statement information, even after controlling for information transmission from alternative trading forums. Out of sample trading strategies confirm the robustness the main findings.     

完善金融衍生产品税制 促进金融市场健康发展

完善我国金融衍生产品税制对金融市场的健康发展有着重要意义.本文分析了我国金融衍生产品税收现状,比较了国际金融衍生产品的税收制度,并在此基础上提出要从三方面完善我国金融衍生产品税制:以法律法规形式明确金融衍生产品税收制度;降低签发和交易环节税负;完善所得环节税收制度.     

Market Efficiency and the Returns to Simple Technical Trading Rules: New Evidence from U.S. Equity Market and Chinese Equity Markets

Numerous studies in the finance literature have investigated technical analysis to determine its validity as an investment tool. This study is an attempt to explore whether some forms of technical analysis can predict stock price movement and make excess profits based on certain trading rules in markets with different efficiency level. To avoid using arbitrarily selected 26 trading rules as did by Brock, Lakonishok and LeBaron (1992) and later by Bessembinder and Chan (1998), this paper examines predictive power and profitability of simple trading rules by expanding their universe of 26 rules to 412 rules. In order to find out the relationship between market efficiency and excess return by applying trading rules, we examine excess return over periods in U.S. markets and also compare the excess returns between U.S. market and Chinese markets. Our results found that there is no evidence at all supporting technical forecast power by these trading rules in U.S. equity index after 1975. During the 1990s break-even costs turned to be negative, –0.06%, even failing to beat a buy-holding strategyin U.S. equity market. In comparison, our results provide support for the technical strategies even in the presence of trading cost in Chinese stock markets.     

Herding behaviour and volatility clustering in financial markets

We propose a financial market model in which speculators follow a linear mix of technical and fundamental trading rules to determine their orders. Volatility clustering arises in our model due to speculators’ herding behaviour. In case of heightened uncertainty, speculators observe other speculators’ actions more closely. Since speculators’ trading behaviour then becomes less heterogeneous, the market maker faces a less balanced excess demand and consequently adjusts prices more strongly. Estimating our model using the method of simulated moments reveals that it is able to explain a number of stylized facts of financial markets quite well. Various robustness checks with respect to the model setup reveal that our results are quite stable.     

Performance of Currency Trading Strategies in Developed and Emerging Markets: Some Striking Differences

Expanding the currency investment universe makes a lot of sense from a diversification point of view. Nevertheless, 60% of the total foreign exchange turnover is still only traded in three currency pairs (USD/EUR, USD/JPY and USD/GBP). The share of trading in local currencies in emerging markets is only around 5%. This can be explained by the fact that some currency managers fear investing in emerging market currencies. Many believe that political risk is the most dominant driver in these markets and that traditional investment rules do not work. In this paper, I apply four technical trading strategies for the developed market currencies and for the most traded emerging market currencies. The empirical results show some striking differences. They suggest that trend-following rules work better for emerging market currencies, while carry trading strategies perform better across developed market currencies. Nevertheless, it seems that conventional techniques could be successfully applied to both developed and emerging market currencies. I conclude that currency managers should not be afraid to diversify into emerging market currencies. They should, however, adjust their trading style accordingly.     

Simple Monetary Policy Rules Under Model Uncertainty

Using stochastic simulations and stability analysis, the paper compares how different monetary policy rules perform in a moderately nonlinear model with a time-varying NAIRU. Rules that perform well in linear models but implicitly embody backward-looking measures of real interest rates (such as conventional Taylor rules) or substantial interest rate smoothing perform very poorly in models with moderate nonlinearities, particularly when policymakers tend to make serially-correlated errors in estimating the NAIRU. This challenges the practice of evaluating policy rules within linear models, in which the consequences of responding myopically to significant overheating are extremely unrealistic.     

Money and stock prices: Market efficiency and the lag in effect of monetary policy

This paper examines stock market efficiency with respect to money supply data by testing (1) regression models of stock returns on monetary variables and (2) trading rules based on money supply data. The evidence indicates no meaningful lag in the effect of monetary policy on the stock market and that no profitable security trading rules using past values of the money supply exist. Therefore this evidence is consistent with the efficient market model. Current security returns incorporate all information contained in past money supply data and, in addition, appear to anticipate future changes in the money supply. A number of previous studies have concluded that lags exist and can be used in profitable trading rules. Analysis of these studies demonstrates that for a variety of reasons the evidence in these past studies does not sustain such conclusions.     

Exchange trading rules and stock market liquidity

We examine stock exchange trading rules for market manipulation, insider trading, and broker–agency conflict, across countries and over time, in 42 stock exchanges around the world. Some stock exchanges have extremely detailed rules that explicitly prohibit specific manipulative practices, but others use less precise and broadly framed rules. We create new indices for market manipulation, insider trading, and broker–agency conflict based on the specific provisions in the trading rules of each stock exchange. We show that differences in exchange trading rules, over time and across markets, significantly affect liquidity.     

An event study of price movements following realized jumps

Price jumps are mostly related to investor reactions to unexpected extreme news. We perform an event study of price movements after jumps to analyse if investors’ reactions are affected by psychological biases. We employ recent non-parametric methods based on intraday returns to separate large price movements that are related to unexpected news from those merely caused by periods of high volatility. In general, we find evidence for irrational pricing, which can be associated with investors’ optimistic behavior in a bull market and the pessimism prevailing in a bear market. Furthermore, our analysis confirms the conjecture that small firms are more subject to speculative trading than large firms.     

Point and density prediction of intra-day volume using Bayesian linear ACV models: evidence from the Polish stock market

Trading volume is one of the key measures of trading activity intensity and plays a crucial role in the financial market microstructure literature. In this paper, we examine the out-of-sample point and density forecasting performance of Bayesian Autoregressive Conditional Volume (ACV) models for intra-day volume data. Based on 5-min traded volume data for stocks quoted on the Warsaw Stock Exchange, a leading stock market in Central and Eastern Europe, we find that, in terms of point forecasts, the considered linear ACV models significantly outperform benchmarks such as the naïve and Rolling Means methods but not necessarily Autoregressive Moving Average (ARMA) models. Moreover, the point forecasts obtained within the exponential error ACV model are significantly superior to those calculated in other competing structures for which Burr or generalized gamma distributions are specified. The main finding from the analysis of density forecasts is that, in many cases, the linear ACV models with the Burr and generalized gamma distributions provide significantly better density forecasts than the linear ACV model with exponential innovations and the ARMA models in terms of the log-predictive score, calibration and sharpness.