scholarly journals A Multilayer Feedforward Perceptron Model in Neural Networks for Predicting Stock Market Short-term Trends

2021 ◽  
Vol 2 (3) ◽  
Author(s):  
Alireza Namdari ◽  
Tariq S. Durrani
Keyword(s):  
Stock Market ◽  
Financial Markets ◽  
Hybrid Model ◽  
Stock Prices ◽  
Stock Price ◽  
Short Term ◽  
Self Organizing Maps ◽  
Hidden Layer ◽  
Low Dimensional ◽  
Nonlinear Autoregressive

AbstractStock market prediction is important for investors seeking a return on the capital invested, though this prediction is a challenging task, due to the complexity of stock price time-series. This task can be performed by conducting two primary analyses: fundamental and technical. In this paper, we examine the predictability of these two analyses using a multilayer feedforward perceptron neural network (MLP) and determine whether MLP is capable of accurately predicting stock market short-term trends. We utilize stock prices (2013 Mar – 2018 Jun) and twelve financial ratios of technology companies selected through a feature selection preprocess. Our model uses self-organizing maps (SOMs) for clustering the historical prices and produces a low-dimensional discretized representation of the input space. The best results are obtained through hyper-parameter optimizations using a three-hidden layer MLP. The models are integrated using a nonlinear autoregressive structure with exogenous input (NARX). We find that the hybrid model successfully predicts the short-term stock trends. The hybrid model yields the greatest directional accuracy (70.36%) as compared to fundamental and technical analyses (64.38% and 62.85%) and state-of-the-art models. The results indicate that the market is not fully efficient. Our model will be useful to practitioners seeking investing and trading opportunities and others interested in the study of financial markets.

scholarly journals ANALYSIS OF MACHINE LEARNING METHODS FOR PREDICTIONS OF STOCK EXCHANGE SHARE PRICES

2021 ◽  
pp. 94-100
Author(s):  
V. Serbin ◽  
U. Zhenisserov
Keyword(s):  
Machine Learning ◽  
Stock Market ◽  
Financial Markets ◽  
Stock Prices ◽  
Stock Price ◽  
Learning Algorithms ◽  
Support Vector ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Price Patterns

Since the stock market is one of the most important areas for investors, stock market price trend prediction is still a hot subject for researchers in both financial and technical fields. Lately, a lot of work has been analyzed and done in the field of machine learning algorithms for analyzing price patterns and predicting stock prices and index changes. Currently, machine-learning methods are receiving a lot of attention for predicting prices in financial markets. The main goal of current research is to improve and develop a system for predicting future prices in financial markets with higher accuracy using machine-learning methods. Precise predicting stock market returns is a very difficult task due to the volatile and non-linear nature of financial stock markets. With the advent of artificial intelligence and machine learning, forecasting methods have become more effective at predicting stock prices. In this article, we looked at the machine learning techniques that have been used to trade stocks to predict price changes before an actual rise or fall in the stock price occurs. In particular, the article discusses in detail the use of support vector machines, linear regression, and prediction using decision stumps, classification using the nearest neighbor algorithm, and the advantages and disadvantages of each method. The paper introduces parameters and variables that can be used to recognize stock price patterns that might be useful in future stock forecasting, and how the boost can be combined with other learning algorithms to improve the accuracy of such forecasting systems.

scholarly journals Systematic optimization of Long Short-Term Memory model for predicting NYSE Arca Airline Index (XAL) during COVID-19

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Sarah Dong ◽  
Amber Wang
Keyword(s):  
Stock Market ◽  
Stock Prices ◽  
Airline Industry ◽  
Stock Price ◽  
Short Term Memory ◽  
The United States ◽  
Short Term ◽  
Term Memory ◽  
Stock Price Prediction ◽  
Long Short Term Memory

Predicting stock prices has been both challenging and controversial. Since it first spread through the United States, the COVID-19 pandemic has impacted the stock market in a multitude of ways. Thus, stock price prediction has become even more challenging. Recurrent neural networks (RNN) have been widely used in many fields to predict financial time series. In this study, Long Short-Term Memory (LSTM), a special form of RNN, is used to predict the stock market direction for the US airline industry by using NYSE Arca Airline Index (XAL). The LSTM model was optimized through changing different hyperparameters of the model architecture to find the best combination for increased accuracy and performance evaluated by several metrics, including raw RMSE (3.51) and MAPA (4.6%), and very high MAPA (95.4%) and R^2 (0.978).

scholarly journals Evolutionary Framework with Bidirectional Long Short-Term Memory Network for Stock Price Prediction

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Hongying Zheng ◽  
Hongyu Wang ◽  
Jianyong Chen
Keyword(s):  
Stock Market ◽  
Stock Prices ◽  
Stock Price ◽  
Short Term Memory ◽  
Optimal Solution ◽  
Short Term ◽  
Term Memory ◽  
Stock Price Prediction ◽  
Memory Network ◽  
Long Short Term Memory

As an important part of the social economy, stock market plays an important role in economic development, and accurate prediction of stock price is important as it can lower the risk of investment decision-making. However, the task of predicting future stock price is very difficult. This difficulty arises from stocks with nonstationary behavior and without any explicit form. In this paper, we propose a novel bidirectional Long Short-Term Memory Network (BiLSTM) framework called evolutionary BiLSTM (EBiLSTM) for the prediction of stock price. In the framework, three independent BiLSTMs correspond to different objective functions and act as mutation individuals, then their respective losses for evolution are calculated, and finally, the optimal objective function is identified by the minimum of loss. Since BiLSTM is effective in the prediction of time series and the evolutionary framework can get an optimal solution for multiple objectives, their combination well adapts to the nonstationary behavior of stock prices. Experiments on several stock market indexes demonstrate that EBiLSTM can achieve better prediction performance than others without the evolutionary operator.

scholarly journals Investigating the use of the method of "nearest neighbors" to predict the behavior of stock prices in the implementation of arbitrage

2014 ◽  
Vol 2 (5) ◽  
pp. 20-30
Author(s):  
Perminov G.
Keyword(s):  
Stock Market ◽  
Stock Prices ◽  
Stock Price ◽  
Price Change ◽  
Nearest Neighbors ◽  
Heuristic Rules ◽  
Short Term ◽  
Sharp Rise ◽  
Two Parameters ◽  
Gains And Losses

In this paper, it was considered one of the types of trading in the stock market - Implementation of arbitrage. The aim of the study was to examine the possibility of using the method of "nearest neighbors" with heuristic rules to predict short-term stock price behavior during arbitrage transactions. In a paper tests the hypothesis that the two parameters - TotalRise (percentage price change over the entire period of growth) and LastChange (percentage change in price over the last day) - are crucial for predicting the behavior of stocks after a sharp rise on positive news. Consequently, an investor might assume, how to behave in the price of the shares, if the result will analyze arbitrage other stocks have close to the value of the shares and TotalRise LastChange. For this action, the risk of loss was defined as the ratio of the neighbors with a loss to all of its neighbors (if 20 neighbors of the action 5 neighbors were unprofitable (i.e. the respective shares rose in price), the riskiness of the operation can be set equal to 25%). Win value was defined as the average of the gains (and losses) of all the neighbors. As a result, developed a model is plausible determines the behavior of the shares.

scholarly journals Hybrid Deep Learning Based Stock Market Prediction with both Sentiment and Historic Trend Data

2020 ◽  
Vol 9 (4) ◽  
pp. 1166-1171
Keyword(s):  
Deep Learning ◽  
Stock Market ◽  
Stock Prices ◽  
Stock Price ◽  
Accurate Prediction ◽  
Short Term ◽  
Stock Market Prediction ◽  
Trend Forecasting ◽  
Trend Data

Stock market is highly volatile and it is necessary for investors to have an accurate prediction of stock prices for a better profitability. Towards this need many methods have been proposed for stock market prediction with aim to provide a higher prediction accuracy. Current methods for stock market prediction are in two categories of machine learning and statistics based. Considering the need for accurate prediction in short term and long term, the merits of both methods must be combined for accurate prediction. This work proposes a hybrid deep learning approach for stock market prediction which combines the historic price-based trend forecasting along with stock market sentiments expressed in twitter to predict the stock price trend.

scholarly journals An Economic Forecasting Method Based on the LightGBM-Optimized LSTM and Time-Series Model

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Jiehua Lv ◽  
Chao Wang ◽  
Wei Gao ◽  
Qiumin Zhao
Keyword(s):  
Decision Making ◽  
Time Series ◽  
Stock Market ◽  
Stock Prices ◽  
Stock Price ◽  
Large Scale ◽  
Stock Index ◽  
Short Term ◽  
Economic Forecasting ◽  
Stock Price Prediction

Stock price prediction is very important in financial decision-making, and it is also the most difficult part of economic forecasting. The factors affecting stock prices are complex and changeable, and stock price fluctuations have a certain degree of randomness. If we can accurately predict stock prices, regulatory authorities can conduct reasonable supervision of the stock market and provide investors with valuable investment decision-making information. As we know, the LSTM (Long Short-Term Memory) algorithm is mainly used in large-scale data mining competitions, but it has not yet been used to predict the stock market. Therefore, this article uses this algorithm to predict the closing price of stocks. As an emerging research field, LSTM is superior to traditional time-series models and machine learning models and is suitable for stock market analysis and forecasting. However, the general LSTM model has some shortcomings, so this paper designs a LightGBM-optimized LSTM to realize short-term stock price forecasting. In order to verify its effectiveness compared with other deep network models such as RNN (Recurrent Neural Network) and GRU (Gated Recurrent Unit), the LightGBM-LSTM, RNN, and GRU are respectively used to predict the Shanghai and Shenzhen 300 indexes. Experimental results show that the LightGBM-LSTM has the highest prediction accuracy and the best ability to track stock index price trends, and its effect is better than the GRU and RNN algorithms.

Macroeconomic Factors and Pakistani Equity Market”

2004 ◽  
Vol 43 (4II) ◽  
pp. 619-637 ◽  
Author(s):  
Muhammad Nishat ◽  
Rozina Shaheen
Keyword(s):  
Stock Market ◽  
Industrial Production ◽  
Stock Prices ◽  
Stock Price ◽  
Consumer Price Index ◽  
Reverse Causality ◽  
Macroeconomic Factors ◽  
Macroeconomic Variables ◽  
Equilibrium Relationships

This paper analyzes long-term equilibrium relationships between a group of macroeconomic variables and the Karachi Stock Exchange Index. The macroeconomic variables are represented by the industrial production index, the consumer price index, M1, and the value of an investment earning the money market rate. We employ a vector error correction model to explore such relationships during 1973:1 to 2004:4. We found that these five variables are cointegrated and two long-term equilibrium relationships exist among these variables. Our results indicated a "causal" relationship between the stock market and the economy. Analysis of our results indicates that industrial production is the largest positive determinant of Pakistani stock prices, while inflation is the largest negative determinant of stock prices in Pakistan. We found that while macroeconomic variables Granger-caused stock price movements, the reverse causality was observed in case of industrial production and stock prices. Furthermore, we found that statistically significant lag lengths between fluctuations in the stock market and changes in the real economy are relatively short.

Impact of FII’s and FDI’s on Indian Stock Market

2016 ◽  
Vol 1 (1) ◽  
Author(s):  
Dr. Kamlesh Kumar Shukla
Keyword(s):  
Stock Market ◽  
Financial Markets ◽  
Global Economy ◽  
Short Term ◽  
Earnings Growth ◽  
The Past ◽  
Bull Market ◽  
Indian Stock Market

FIIs are companies registered outside India. In the past four years there has been more than $41 trillion worth of FII funds invested in India. This has been one of the major reasons on the bull market witnessing unprecedented growth with the BSE Sensex rising 221% in absolute terms in this span. The present downfall of the market too is influenced as these FIIs are taking out some of their invested money. Though there is a lot of value in this market and fundamentally there is a lot of upside in it. For long-term value investors, there’s little because for worry but short term traders are adversely getting affected by the role of FIIs are playing at the present. Investors should not panic and should remain invested in sectors where underlying earnings growth has little to do with financial markets or global economy.

Prior Return Effect in Indian Stock Market: An Intra-day Analysis

2015 ◽  
Vol 5 (1) ◽  
Author(s):  
Vanita Tripathi ◽  
Shalini Aggarwal
Keyword(s):  
Stock Market ◽  
Stock Prices ◽  
High Frequency ◽  
Good News ◽  
High Frequency Data ◽  
Short Term ◽  
Fund Managers ◽  
News Events ◽  
Return Effect ◽  
Indian Stock Market

In a first of this kind, this paper examines the issue of prior return effect in Indian stock market in intra-day analysis using high frequency data. We document that in Indian stock market, security returns exhibit a reversal in their direction within few minutes of extreme price rises as well as price falls. However the speed with which the correction takes place is slightly different for good news events and bad news events. Indian investors tend to be optimistic as they immediately bring stock prices up following unjustified price falls but take time to bring stock prices down following unjustified price rises. These findings lend a further support to short-term overreaction literature. More importantly, these findings serve as a proof of predictability of the direction of future stock prices and consequent returns on an intra-day basis. It forwards important investment implications for traders, fund managers, and investors at large.

scholarly journals Building stock market resilience through digital transformation: using Google trends to analyze the impact of COVID-19 pandemic

2020 ◽  
Vol 14 (1) ◽  
Author(s):  
Ding Ding ◽  
Chong Guan ◽  
Calvin M. L. Chan ◽  
Wenting Liu
Keyword(s):  
Stock Market ◽  
Stock Prices ◽  
Stock Price ◽  
Digital Transformation ◽  
Google Trends ◽  
Building Stock ◽  
Market Sentiment ◽  
Price Performance ◽  
Novel Coronavirus ◽  
The Impact

Abstract As the 2019 novel coronavirus disease (COVID-19) pandemic rages globally, its impact has been felt in the stock markets around the world. Amidst the gloomy economic outlook, certain sectors seem to have survived better than others. This paper aims to investigate the sectors that have performed better even as market sentiment is affected by the pandemic. The daily closing stock prices of a total usable sample of 1,567 firms from 37 sectors are first analyzed using a combination of hierarchical clustering and shape-based distance (SBD) measures. Market sentiment is modeled from Google Trends on the COVID-19 pandemic. This is then analyzed against the time series of daily closing stock prices using augmented vector autoregression (VAR). The empirical results indicate that market sentiment towards the pandemic has significant effects on the stock prices of the sectors. Particularly, the stock price performance across sectors is differentiated by the level of the digital transformation of sectors, with those that are most digitally transformed, showing resilience towards negative market sentiment on the pandemic. This study contributes to the existing literature by incorporating search trends to analyze market sentiment, and by showing that digital transformation moderated the stock market resilience of firms against concern over the COVID-19 outbreak.

Sign in / Sign up

Export Citation Format

Share Document