A Pairs Trading Strategy for Goog/googl Using Machine Learning

نویسنده

  • Jiayu Wu
چکیده

bag of related financial instruments to make profits by exploiting their relations. One important feature of pairs trading is that it is market-neutral, which is particularly appealing in the current volatile and unpredictable macro-economic environments. In this project, we will use the spread model, the O-U meanreverting model, and SVM to build a trading strategy and apply the strategy to GOOG/GOOGL. We will first illustrate the spread model and the O-U meanreverting in detail. Unlike most previous work that only takes price spread into consideration, we will also use the spread model and the O-U mean-reverting model to model the two securities' technical indicators. In other words, we extend the concept of ``spread'' by also investigating technical indicators' spread. We will construct trading signals by processing different kinds of ``spreads'' and then use these trading signals as input features for SVM classification. Instead of using the traditional back-testing method to test our trading strategy, we will use SVM binary classification to measure our trading strategy. To achieve that, we will reconstruct the original pricing feeds to labeled examples, and there are two methods we use to reconstruct the labeled examples, one for measuring the strategy's ability to seize profit opportunities, and the other for measuring the strategy's ability to make directional predictions. One important thing for a pairs trading strategy is to select a proper pair of financial instrucments. For example, if the price of security A always rises when the price of security B rises, it seems that A and B may be used for pairs trading. However, the explicit relation between prices may not be good enough for a good pair. The good pairs should share as many the same intrinsic characteristics as possible. GOOG/GOOGL are both shares of Google Inc. (nos Alphabet Inc.) but with different vote rights. GOOGL represents Class A shares while GOOG represents Class C shares. Only Class A shares have voting rights. Therefore, generally, the price of GOOGL is slightly higher than that of GOOG. Other than voting rights, they are essentially the same since their prices are based upon the same fundamentals. ð Jiayu Wu, [email protected] A PAIRS TRADING STRATEGY FOR GOOG/GOOGL USING MACHINE LEARNING

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Using Random Forests in conintegrated pairs trading

In this thesis we will use Random Forests to define a trading strategy. Using this powerful machine learning technique, we will try to predict the daily price changes of financial products that move similarly over the long term, so-called cointegrated pairs. We propose a way to adjust our portfolio based on these prediction, while limiting our risk. Firstly, we test our strategy on data generat...

متن کامل

Deep Reinforcement Learning for Pairs Trading

Reinforcement learning (RL) [1] differs from traditional supervised machine learning in the sense that it not only considers short-term consequences of actions/decisions, but also long-term outcomes. Because of recent advances in deep learning, model-free deep reinforcement learning (DRL) has proven successful in various applications, as with the success of a deep Q-network (DQN) in the Atari g...

متن کامل

Trading the Twitter Sentiment with Reinforcement Learning

This paper is to explore the possibility to use alternative data and artificial intelligence techniques to trade stocks. The efficacy of the daily Twitter sentiment on predicting the stock return is examined using machine learning methods. Reinforcement learning(Q-learning) is applied to generate the optimal trading policy based on the sentiment signal. The predicting power of the sentiment sig...

متن کامل

Modeling and Trading the EUR/USD Exchange Rate Using Machine Learning Techniques

The present paper aims in investigating the performance of state-of-the-art machine learning techniques in trading with the EUR/USD exchange rate at the ECB fixing. For this purpose, five supervised learning classification techniques (K-Nearest Neighbors algorithm, Naïve Bayesian Classifier, Artificial Neural Networks, Support Vector Machines and Random Forests) were applied in the problem of t...

متن کامل

Algorithmic Trading of Futures via Machine Learning

A lgorithmic trading of securities has become a staple of modern approaches to financial investment. In this project, I attempt to obtain an effective strategy for trading a collection of 27 financial futures based solely on their past trading data. All of the strategies that I consider are based on predictions of the future price and volatility of the various securities under consideration, an...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015