Stock Price Prediction Based on Social Network * A survey

Report
Stock Price Prediction Based on
Social Network
— A survey
Presented by: CHEN En
Outline
 Introduction
 Related work
 Methodology
 Conclusion
Outline
 Introduction
 Related work
 Methodology
 Conclusion
Introduction
 Stock price prediction
 Act of trying to determine the future value of company stock or other
financial instrument trade on financial exchange
 Successful prediction could yield significant profit!
Introduction
 The efficient-market hypothesis
 Stock price movement are governed by the random walk hypothesis
 Inherently unpredictable
 However, the others disagree and possess myriad
prediction methods to gain future price information

Fundamental analysis
- Performance ratio (i.e. P/E ratio)

Technical analysis
- Charting analysis (i.e. Head and shoulder)

Alternative methods
- Internet-based data source for prediction
Outline
 Introduction
 Related work
 Methodology
 Conclusion
Related work
 Traditional investment decision approaches:
 Capital asset pricing model (CAMP)
 Arbitrage pricing theory (APT)
 Unrealistic and time complexity of the required calculation
make them not applicable in real world problem
 Current soft computing techniques:



Neural network (NN) (A. N. Refenes, M. Azema-Barac, and A. D. Zapranis1993)
Genetic algorithm (GA) (R. Riolo, T. Soule, B. Eorzel2008)
Support Vector Machines (SVM) (G. H. John, P. Miller, and R. Kerber1996)
Because of widely use of the social network, major prediction
are based on these public information.
Related work
 Why social network?
 Ubiquitous and important for content sharing

Facebook, Blog, Twitter feeds, etc.

Public information—easily obtained

Behavioral economics demonstrate that emotions can profoundly
affect individual behavior and decision-making

Recent research suggests very early acting prediction indicators can
be extracted from online social media



Online chat activity predicts book sales (Gruhl, D, Guha, R, Kumar, R, Novak, J2005)
Blog sentiment predicts movie sales (Mishne, G & Glance, N.2006)
Consumer spending indicate disease infection rates (Choi, H & Varian, H.2009)
Outline
 Introduction
 Related work
 Methodology
 Conclusion
Method 1: Twitter message and the stock price
 Analysis of the relation between twitter messages and stock
market index

Selection of happiness and unhappiness words
Method 1: Twitter message and the stock price
 Analysis of the relation between twitter messages and stock
market index


Selection of happiness and unhappiness words
Evaluating both happiness and unhappiness words in the same tweet

Where f=frequency of i’th word, Avg_happiness(wordi)=happiness value
of word and Avg(T)=average happiness of given tweet
Method 2: Twitter mood predicts the stock price
 Analyzing the text content of daily Twitter feeds to find the
correlation between stock price and twitter mood

Phase 1: Using two mood tracking tools: OpinionFinder & GoogleProfile of Mood states (GPOMs) to extract feature of mood


OpinionFinder: Positive vs. nagetive mood
GPOMs: Calm, Alert, Sure, Vital, Kind, and Happy

Phase 2: Granger causality analysis to test correlation between Dow
Jones Industrial average (DJIA) values and GPOMs and OF values

Phase 3: Deploying a Self-Organizing Fuzzy Neural Network model (nonlinear model) to test the hypothesis
Method 2: Twitter mood predicts the stock price
Method 3: Technical analysis with sentiment
 Combining technical analysis with sentiment analysis for
stock prediction

Extract feature (using SentiWordNet):




Time series data (price and volume) source
Social network source (on Engadget)
Technical indicators
Using a multiple kernel learning framework to learn and prediction
the stock price
Method 3: Technical analysis with sentiment
Technical analysis
Emotion analysis
Outline
 Introduction
 Related work
 Methodology
 Conclusion
Conclusion
 Method 1: It is naïve but useful to predict the stock price
index by just using happiness and unhappiness
 Method 2: The result showed that changes in the public
mood state could indeed be tracked from the content of
large-scale Twitter feed using simple text processing
techniques.
 Method 3: It is considerable to use multiple kernel learning
that covers several features.

similar documents