This article originally appeared on Technology.org
---
In 1973, Princeton University professor Burton Malkiel claimed in his bestselling book, A Random Walk Down Wall Street, that “A blindfolded monkey throwing darts at a newspaper’s financial pages could select a portfolio that would do just as well as one carefully selected by experts.” While what the professor said was hilarious, this research paper explores the effectiveness of AI in Stock Market Prediction, which, at least theoretically, could improve market predictions compared to the human baseline.
Sohrab Mokhtari, Kang K Yen and Jin Liu have discussed this in their research paper titled “Effectiveness of Artificial Intelligence in Stock Market Prediction Based on Machine Learning”, which forms the basis of the following text.
Importance of this research
Stock markets are a very lucrative and popular way to grow capital. The use of AI in stock market prediction is also growing increasingly popular. Blindly trusting AI to invest money in the stock market could lead to loss of capital for the investors. The research paper evaluates if AI can predict the stock market with reliable accuracy.
Analyzing Stock Market
The below two broad methodologies can be used to analyze a stock in the stock market:
- Fundamental Analysis: This school of thought tries to calculate the intrinsic value of a share based on the company’s revenue, profitability, liquidity & operating efficiency. Ideally, if the intrinsic value is more than its LTP (last traded price), it should be bought, and if its intrinsic value is less than its LTP, it should be sold.
- Technical Analysis: This methodology uses past data of the price of the stock using parameters such as relative strength index (RSI), moving average convergence/divergence (MACD), and money flow index (MFI) and tries to time the market. If the technical analysis suggests that the stock price would go high, it will trigger a buy call & if the analysis indicates that the stock price would go low, it will trigger a sell call.
Modelling Stock Market
- Efficient Market Hypothesis (EHM): This hypothesis suggests that a stock price moves in the direction of public sentiment that is a reaction to recently published news aggregation.
- Adaptive Market Hypothesis (AHM): AHM tries to predict the market trend using psychology-based theories.
The problem statement & the underlying motivation are described in detail in the research paper. The research paper also measures the performance of ML algorithms on a stock market testbed.
Conclusion
In this research paper, ML models were not found to be an effective predictor of the stock market. In the words of the researchers
This study tries to address the problem of stock market prediction leveraging ML algorithms. To do so, two main categories of stock market analysis (technical and fundamental) are considered. The performance of ML algorithms on the forecast of the stock market is investigated based on both of these categories. For this, labeled datasets are used to train the supervised learning algorithms, and evaluation metrics are employed to examine the accuracy of ML algorithms in the prediction process. The results show that the linear regression model predicts the closing price remarkably with a shallow error value in the technical analysis. Moreover, in the fundamental analysis, the SVM model can predict public sentiment with an accuracy of 76%. These results imply that although AI can predict the stock price trends or public sentiment about the stock markets, its accuracy is not good enough. Furthermore, while the linear regression can predict the closing price with a sensible range of error, it cannot precisely predict the same value for the next business day. Thus, this model is not sufficient for long-term investments. On the other hand, the accuracy of classification algorithms in predicting buying, selling, or holding a stock is not satisfying enough and can result in loss of capital. Based on this study, it seems that AI is not close to the prediction of the stock market with reliable accuracy.
Source: Sohrab Mokhtari, Kang K Yen and Jin Liu’s “Effectiveness of Artificial Intelligence in Stock Market Prediction Based on Machine Learning”
