China
Africa
Explore chapters and articles related to this topic
Application of machine learning algorithms to improve stock prediction using technical indicators
Published in Sheela Evangeline, M.R. Rajkumar, Saritha G. Parambath, Recent Advances in Materials, Mechanics and Management, 2019
R.K. Dhanya, V.S. Unnikrishnan
A stock market is a public place of high popular investment owing to the investors. It has been a place to trade the company’s stocks and derivatives at an approved stock price. It behaves like a chaos system that means the behavioural traits of share prices are unpredictable and uncertain [1]. The two most important features of stock markets are risk and return. The minimization of risk with maximum return is the main objective of investor who invested in stock market. However, stock market is interacted with many factors such as political events, general economic conditions and traders’ expectation. So the fluctuating behavior of stock market makes it difficult to predict the real time stock prices. Researchers have been studying to forecast the stock market price as precisely as possible to reach the best investment decisions. Many studies have existed for predicting stock prices on the basis of fundamental, technical and technological analysis. Fundamental analysis, one of the methods that examines the company performance, economic environment and industrial performance to derive the future stock’s price [6]. It evaluates a stock by attempting to measure its intrinsic value by examining related economic, financial and other qualitative and quantitative factors. Another important tool used for stock prediction is technical analysis which stands in contrast to the fundamental analysis approach to security and stock analysis. The charts and indicators of technical analysis help to know the movement of stock prices. Technical analysts use technical indicators to look into a different perspective from which stock prices can be analyzed. Technical indicators provide unique outlook on the strength and direction of the underlying price action for a given time frame. It serves three main functions: to alert, to confirm and to predict. Every stock has unique characteristics. For that reason, a particular type of technical indicator might not be a good predictor for every stocks. It should be good to use different features of technical indicators for prediction attempt in different time periods and or different stocks. The above two techniques may not be a good alternative solution for common investors [2]. Recently, stock market prediction has since moved in to the technological analysis. The most prominent technique involves the use of machine learning algorithms. The field of machine learning describes a variety of learning paradigms, algorithms and theoretical results. It draws on results from artificial intelligence, probability and statistics, computational complexity theory, control theory, information theory and other fields [5]. Numerous studies have been conducted to predict the stock prices using machine learning algorithms. Predicting stock price is difficult due to uncertainties involved. In this paper, we proposed Naive Bayes, Decision Tree, Random Forest, Decision Tree with AdaBoost algorithms for predicting stock prices using technical indicators and to compare the performance of these models. The results demonstrate that the ensemble method AdaBoost makes the decision tree outperforms other models.
Ensemble Classifier for Stock Trading Recommendation
Published in Applied Artificial Intelligence, 2022
In financial markets, technical analysis develops technical indicators and several charts from historical prices and uses them to predict trends or provide trading signals (Hu et al. 2015; Lorenzo 2013). There are hundreds of technical indicators developed for the past decades, but the most popular ones are limited to fewer than 20 of them. Technical indicators can be classified into four types – trend, momentum, volume, and volatility (Hu et al. 2015). First, trend indicators tell us which direction the price is moving in, upward, downward, or sideway – there is no trend. Simple Moving Average (SMA) and Exponential Moving Average (EMA) are the most popular examples of trend indicators. Second, momentum indicators evaluate the velocity of price change and judge whether a reversal is about to happen. Common momentum indicators are Moving Average Convergence Divergence (MACD), Stochastic Oscillator (%K and %D), and Relative Strength Index (RSI). Third, volume indicators measure the strength of a trend or confirm a trading direction based on some form of averaged volume traded. A popular volume indicator is On Balance Volume (OBV). Fourth, volatility indicator measures the range of price movement and can be used to identify level of support and resistance. Common volatility indicator includes Bollinger Band (BB) (Hu et al. 2015; Lorenzo 2013).
Blended computation of machine learning with the recurrent neural network for intra-day stock market movement prediction using a multi-level classifier
Published in International Journal of Computers and Applications, 2021
Krishna Kumar, Md. Tanwir Uddin Haider
Technical indicators [27] are mathematical calculations based on the market data such as stock price and volume to perform the technical analysis over the data to identify the market behavior like trend and momentum for future prediction. In our proposed work, we have calculated these statistics based on the intra-day trading model, obtaining the set of technical indicators that are best suited for intra-day trading and gives the best features or predictor through which the accuracy can be maximized.