Academic journal article IUP Journal of Applied Finance

# Application of Machine Learning Tools in Predictive Modeling of Pairs Trade in Indian Stock Market [Dagger]

Academic journal article IUP Journal of Applied Finance

# Application of Machine Learning Tools in Predictive Modeling of Pairs Trade in Indian Stock Market [Dagger]

## Article excerpt

(ProQuest: ... denotes formulae omitted.)

Introduction

Pairs Trading is an arbitrage strategy which generates profits from the movement in the ratio of prices of two stocks. Ideally, the ratio of the price of the two stocks, which belong to the same sector and whose prices are highly correlated, should be stable. However, given the inherent randomness of stock price movements, this ratio may fluctuate. The fundamental basis of pairs trading is that although there would be fluctuations in the ratio of the prices, it would be mean reverting. Thus if the ratio rises, it is expected that it would fall and if the ratio falls, then it is expected to rise. For the ratio to rise, one reason could be that the price of one stock is rising at a faster rate than the other one, in spite of the fact that they are from the same sector and are having highly correlated prices. The trading strategy in this case is to short the faster moving stock and long the slower moving stock; the expectation being that the stock whose price is rising faster will fall, and the stock whose price is not rising that fast, will continue to rise. Similarly, if the ratio falls, then we long the faster falling one and short the slower falling one. Clearly, if a framework could be devised to predict the future movement in the ratio of stock prices, it would be helpful for such trading.

This paper tries to build an analytical framework to forecast the value of the ratio of a pair of share prices. We consider daily data on ratio of stock prices, its lagged values, the departure of the ratio from the mean and technical indicators like momentum and Bollinger Band calculated around this price ratio. These factors are then built into a nonlinear learning framework for analysis and prediction. Our contention is that, if movement in the ratio of a pair of share prices can be predicted, then one can take strategic trading positions and profit from trading.

The ratio of two share prices can rise or fall depending on the relative movement of the numerator and the denominator. Table 1 shows the various possibilities.

As the movement in the price ratio not only depends on the absolute rise and fall in the two prices, but also on their rate of change, we incorporate a technical indicator, momentum, in our study. The mean reverting property of a ratio of prices is incorporated through the extent of deviation from the mean as an explanatory variable. Further, if there is reversal, there must exist ceilings and floors. This we incorporate through values of the ratio +2 a where a is the standard deviation of the ratio of prices. This latter variable is called the Bollinger Band in technical analysis and is constructed on moving average of prices.

Literature Review

This paper draws on two strands of the literature. One is the financial literature on pairs trading and the other is applications of machine learning tools in the area of finance. We provide a brief overview of both in this section.

Nath (2003) uses the distance method for pair trading. The distance is calculated as the sum of squares of distances of prices from a measure of central tendency, normalized by the standard deviation. A trade is initiated when the distance between the securities in that pair widens to reach or cross a trigger. The trade is closed generally when the spread narrows, or the last day of the trading period is reached, or when the distance widens to hit a risk management trigger level.

Vidyamurthy (2004) gives a detailed analysis of pairs trading from both the statistical arbitrage point of view and the risk arbitrage point of view. His approach to pairs trading is based on the literature on co-integration and related estimation techniques.

Whistler (2004) points out the role of technical analysis and fundamental analysis in pairs trading. All the basic concepts are explained to provide clarity to the concepts and the relationships that a trader has to keep in mind for such trades. …

Search by...
Show...

### Oops!

An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.