scholarly journals Information Theoretic Causality Detection between Financial and Sentiment Data

Entropy ◽  
2021 ◽  
Vol 23 (5) ◽  
pp. 621
Author(s):  
Roberta Scaramozzino ◽  
Paola Cerchiello ◽  
Tomaso Aste
Keyword(s):  
Social Media ◽  
Stock Market ◽  
Stock Price ◽  
Transfer Entropy ◽  
Market Prices ◽  
Causal Information ◽  
Information Theoretic ◽  
P Index ◽  
Media Sentiment

The interaction between the flow of sentiment expressed on blogs and media and the dynamics of the stock market prices are analyzed through an information-theoretic measure, the transfer entropy, to quantify causality relations. We analyzed daily stock price and daily social media sentiment for the top 50 companies in the Standard & Poor (S&P) index during the period from November 2018 to November 2020. We also analyzed news mentioning these companies during the same period. We found that there is a causal flux of information that links those companies. The largest fraction of significant causal links is between prices and between sentiments, but there is also significant causal information which goes both ways from sentiment to prices and from prices to sentiment. We observe that the strongest causal signal between sentiment and prices is associated with the Tech sector.

scholarly journals Differences In Intrinsic Value With Stock Market Prices Using The Price Earning Ratio (Per) Approach As An Investment Decision Making Indicator (Case Study Of Manufacturing Companies In Indonesia Period 2016 - 2017)

2019 ◽  
Vol 1 (1) ◽  
pp. 82-92
Author(s):  
Ardy Indra Lekso Wibowo Putra ◽  
Aditya Dwiansyah Putra ◽  
Murni Sari Dewi ◽  
Denny Oktavina Radianto
Keyword(s):  
Decision Making ◽  
Stock Market ◽  
Stock Price ◽  
Stock Exchange ◽  
Intrinsic Value ◽  
Investment Decision ◽  
Manufacturing Companies ◽  
Market Prices ◽  
Investment Decision Making

An investor must be able to consider all kinds of steps that will be taken or that will be carried out, assessing stocks - shares that will provide optimal benefits in making an investment decision. By analyzing the intrinsic value of the price of a company's stock, investors can assess the fairness of the stock price. The method used to analize intrinsic value is fundamental analysis using the Price Earning Ratio (PER) approach. The samples to be taken in this research are manufacturing companies in Indonesia which are listed on the Indonesia Stock Exchange (IDX) for the period 2016 - 2017 with certain criteria. The results of this research will show that the shares of companies listed are in overvalued, undervalued or correctly valued conditions. So investors can decide to buy, hold or sell their shares.

scholarly journals Stock Picker using Machine Learning

2020 ◽  
Vol 8 (6) ◽  
pp. 3912-3914
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Stock Market ◽  
Stock Price ◽  
Historical Data ◽  
Great Accuracy ◽  
Current Data ◽  
Random Forest Classifier ◽  
Market Prices ◽  
Market Institution

The main objective of this paper is to build a model to predict the value of stock market prices from the previous year's data. This project starts with collecting the stock price data and pre-processing the data. 12 years dataset is used to train the model by the Random Forest classifier algorithm. Backtesting is the most important part of the quantitative strategy by which the accuracy of the model is obtained. Then the current data is collected from yahoo finance and the data is fed to the model. Then the model will predict the stock that is going to perform well based on its learning from the historical data. This model predicted the stocks with great accuracy and it can be used in the stock market institution for finding the good stock in that index.

scholarly journals Learning-Based Stock Market Trending Analysis by Incorporating Social Media Sentiment Analysis

2021 ◽  
Author(s):  
Zhaoxia Wang ◽  
Zhenda HU ◽  
Fang LI ◽  
Seng-Beng HO
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Stock Market ◽  
Sentiment Analysis ◽  
Prediction Performance ◽  
Support Vector ◽  
Stock Market Prediction ◽  
Stock Price Prediction ◽  
Extreme Gradient Boosting ◽  
Media Sentiment

Abstract Stock market trending analysis is one of the key research topics in financial analysis. Various theories once highlighted the non-viability of stock market prediction. With the advent of machine learning and Artificial Intelligence (AI), more and more efforts have been devoted to this research area, and predicting the stock market has been demonstrated to be possible. Learning-based methods have been popularly studied for stock price prediction. However, due to the dynamic nature of the stock market and its non-linearity, stock market prediction is still one of the most dificult tasks. With the rise of social networks, huge amount of data is being generated every day and there is a gaining in popularity of incorporating these data into prediction model in the effort to enhance the prediction performance. Therefore, this paper explores the possibilities of the viability of learning-based stock market trending prediction by incorporating social media sentiment analysis. Six machine learning methods including Multi-Layer Perception, Support Vector Machine, Naïve Bayes, Random Forest, Logistic Regression and Extreme Gradient Boosting are selected as the baseline model. The result indicates the possibilities of successful stock market trending prediction and the performance of different learning-based methods is discussed. It is discovered that the distribution of the value of stocks may affect the prediction performance of the methods involved. This research not only demonstrates the merits and weaknesses of different learning-based methods, but also points out that incorporating social opinion is a right direction for improving the performance of stock market trending prediction.

Interaction Between Forex and Stock Markets in India: An Entropy Approach

2008 ◽  
Vol 33 (4) ◽  
pp. 27-46 ◽  
Author(s):  
Y V Reddy ◽  
A Sebastin
Keyword(s):  
Time Series ◽  
Mutual Information ◽  
Stock Market ◽  
Transfer Entropy ◽  
The Other ◽  
Stock Index ◽  
Reverse Direction ◽  
Probability Mass Function ◽  
Information Theoretic ◽  
The Relationship

Interactions between the foreign exchange market and the stock market of a country are considered to be an important internal force of the markets in a financially liberalized environment. If causal relationship from a market to the other is not detected, then informational efficiency exists in the other whereas existence of causality implies that hedging of exposure to one market by taking position in the other market will be effective. The temporal relationship between the forex market and the stock market of developing and developed countries has been studied, especially after the East Asian financial crisis of 1997–98, using various methods like cross-correlation, cross-spectrum, and error correction model, but these methods identify only linear relations. A statistically rigorous approach to the detection of interdependence, including non-linear dynamic relationships, between time series is provided by tools defined using the information theoretic concept of entropy. Entropy is the amount of disorder in the system and also is the amount of information needed to predict the next measurement with a certain precision. The mutual information between two random variables X and Y with a joint probability mass function p(x,y) and marginal mass functions p(x) and p(y), is defined as the relative entropy between the joint distribution p(x,y) and the product distribution p(x)*p(y). Mutual information is the reduction in the uncertainty of X due to the knowledge of Y and vice versa. Since mutual information measures the deviation from independence of the variables, it has been proposed as a tool to measure the relationship between financial market segments. However, mutual information is a symmetric measure and does not contain either dynamic information or directional sense. Even time delayed mutual information does not distinguish information actually exchanged from shared information due to a common input signal or history and therefore does not quantify the actual overlap of the information content of two variables. Another information theoretic measure called transfer entropy has been introduced by Thomas Schreiber (2000) to study the relationship between dynamic systems; the concept has also been applied by some authors to study the causal structure between financial time series. In this paper, an attempt has been made to study the interaction between the stock and the forex markets in India by computing transfer entropy between daily data series of the 50 stock index of the National Stock Exchange of India Limited, viz., Nifty and the exchange rate of Indian Rupee vis- à- vis US Dollar, viz., Reserve Bank of India reference rate. The entire period–November 1995 to March 2007–selected for the study, has been divided into three sub-periods for the purpose of analysis, considering the developments that took place during these sub-periods. The results obtained reveal that: there exist only low level interactions between the stock and the forex markets of India at a time scale of a day or less, although theory suggests interactive relationship between the two markets the flow from the stock market to the forex market is more pronounced than the flow in the reverse direction.

scholarly journals Stock Market Prices Prediction using Random Forest and Extra Tree Regression

2019 ◽  
Vol 8 (3) ◽  
pp. 1224-1228
Keyword(s):  
Machine Learning ◽  
Stock Market ◽  
Stock Prices ◽  
Stock Price ◽  
Stock Exchange ◽  
Research Area ◽  
Support Vector ◽  
Market Prices ◽  
Machine Learning Approach ◽  
Innovative Work

Prediction of Stock price is now a day’s an existing and interesting research area in financial and academic sectors to know the scale of economies. There did not exists any significant set of rules to estimate and predict the scale of share in the stock exchange. Many evolutionary technologies are existing such as technical, fundamental, time, statistical and series analysis which help us to attempt the prediction process, but none of the methods are proved as reliable and accurate tool to the society in the estimation of stock exchange or share market scales. Here in this paper we attempted to do innovative work through Machine Learning approach to predict or sense the behaviour tracking of the stock market sensex. Linear regression, Support Vector regression, Decision Tree, Ramdom Forest Regressor and Extra Tree Regressor are the Machine Learning models implemented effectively in predicting the stock prices and define the activity between the exchanges the securities between the buyers and sellers. We predicted the price of the stock based on the closing value and stock price. An algorithm with high accuracy we do the process of comparison for the accuracy of each of the model and finally is considered as better algorithm for predicting stock price. As share market is a vague domain we cannot predict the conditions occur, and also share market can never be predicted, this job can be done easily and technically through this work and the main aim of this paper is to apply algorithms in Machine Learning in predicting the stock prices.

scholarly journals STOCK PRICE TREND PREDICTION USING SUPPORT VECTOR MACHINE AND CORAL REEF OPTIMIZATION ALGORITHM

2020 ◽  
Vol 18 (1) ◽  
pp. 68-87
Author(s):  
A. DEJI-OLARERIN ◽  
O. FOLORUNSO ◽  
O. R. VINCENT ◽  
O. M. OLAYIWOLA
Keyword(s):  
Coral Reef ◽  
Stock Market ◽  
Optimization Algorithm ◽  
Stock Price ◽  
Optimization Problems ◽  
Series Data ◽  
Support Vector ◽  
Trend Prediction ◽  
Market Prices ◽  
Price Trend

Due to non-linearity and non-stationary characteristics of stock market time series data, prior approaches have not been adequate enough for predicting stock market prices. Support vector machines are classifier that have been reported in the literature as having good recognition accuracy and have been applied in the area of predicting financial stock market prices and was found efficient. It is however noted that the performance of the SVM is affected by the values of the hyper-parameters used by the SVM. There is the need to find a way for searching for the best hyper-parameters that optimizes the performance of an SVM model. Coral Reef Optimization (CRO) is one of many nature-inspired algorithms used extensively to solve optimization problems. It is very effective in solving optimization problems because it is able to achieve global optimization. This paper’s contribution is the development of Coral Reef search algorithms for the improvement of the hyper-parameters of the SVM used for stock price trend prediction. The Algorithm is validated using stock data of two banks. The results obtained out-performed un-optimized SVM, and have the same performance as that of SVM optimized with the FireFly optimization algorithm.    

scholarly journals When the Going Gets Tough, The Tweets Get Going! An Exploratory Analysis of Tweets Sentiments in the Stock Market

2018 ◽  
Vol 18 (5) ◽  
Keyword(s):  
Social Media ◽  
Stock Market ◽  
Subject Matter ◽  
Stock Prices ◽  
Stock Price ◽  
Asset Prices ◽  
Exploratory Analysis ◽  
Information Networks ◽  
Digital Information ◽  
Stock Performance

Information artifacts in social media can have significant impact on domains and subject matter opinions. Asset prices, stock prices and volumes, and metrics are influenced by turbulence in their information ecosystems. Analyses of digital information networks and social media information events have shown information artifacts to affect stock performance without consistent correlation to fundamentals. Thus it becomes important to dispel ambiguity and gain insights into how the sentiments associated with information artifacts in Twitter (due to its extensive usage in relevant signaling), are associated with equity movements. Using an exploratory analysis to study tweet sentiment, we link stock price variations, and explore associated metrics. Our tweets analytics deploying textual analytics, identifies forms in tweet behavior and sentiment shifts.

scholarly journals Information-theoretic measures for nonlinear causality detection: application to social media sentiment and cryptocurrency prices

2020 ◽  
Vol 7 (9) ◽  
pp. 200863
Author(s):  
Z. Keskin ◽  
T. Aste
Keyword(s):  
Time Series ◽  
Information Transfer ◽  
Synthetic Data ◽  
Transfer Entropy ◽  
Significant Information ◽  
Information Theoretic ◽  
Order Of Magnitude ◽  
Information Theoretic Measures ◽  
Media Sentiment ◽  
Non Parametric

Information transfer between time series is calculated using the asymmetric information-theoretic measure known as transfer entropy. Geweke’s autoregressive formulation of Granger causality is used to compute linear transfer entropy, and Schreiber’s general, non-parametric, information-theoretic formulation is used to quantify nonlinear transfer entropy. We first validate these measures against synthetic data. Then we apply these measures to detect statistical causality between social sentiment changes and cryptocurrency returns. We validate results by performing permutation tests by shuffling the time series, and calculate the Z -score. We also investigate different approaches for partitioning in non-parametric density estimation which can improve the significance. Using these techniques on sentiment and price data over a 48-month period to August 2018, for four major cryptocurrencies, namely bitcoin (BTC), ripple (XRP), litecoin (LTC) and ethereum (ETH), we detect significant information transfer, on hourly timescales, with greater net information transfer from sentiment to price for XRP and LTC, and instead from price to sentiment for BTC and ETH. We report the scale of nonlinear statistical causality to be an order of magnitude larger than the linear case.

Sign in / Sign up

Export Citation Format

Share Document