AI System – Using Neural Networks With Deep Learning – Beats Stock Market in Simulation

AI Stock Market Concept

Researchers combined convolutional neural networks (CNNs) with deep learning to develop a market forecasting system that may have greater gains and fewer losses than previous AI-based attempts to manage stock portfolios.

Researchers in Italy have melded the emerging science of convolutional neural networks (CNNs) with deep learning — a discipline within artificial intelligence — to achieve a system of market forecasting with the potential for greater gains and fewer losses than previous attempts to use AI methods to manage stock portfolios. The team, led by Prof. Silvio Barra at the University of Cagliari, published their findings on IEEE/CAA Journal of Automatica Sinica.

The University of Cagliari-based team set out to create an AI-managed “buy and hold” (B&H) strategy — a system of deciding whether to take one of three possible actions — a long action (buying a stock and selling it before the market closes), a short action (selling a stock, then buying it back before the market closes), and a hold (deciding not to invest in a stock that day). At the heart of their proposed system is an automated cycle of analyzing layered images generated from current and past market data. Older B&H systems based their decisions on machine learning, a discipline that leans heavily on predictions based on past performance.

By letting their proposed network analyze current data layered over past data, they are taking market forecasting a step further, allowing for a type of learning that more closely mirrors the intuition of a seasoned investor rather than a robot. Their proposed network can adjust its buy/sell thresholds based on what is happening both in the present moment and the past. Taking into account present-day factors increases the yield over both random guessing and trading algorithms not capable of real-time learning.

To train their CNN for the experiment, the research team used S&P 500 data from 2009 to 2016. The S&P 500 is widely regarded as a litmus test for the health of the overall global market.

At first, their proposed trading system predicted the market with about 50 percent accuracy, or about accurate enough to break even in a real-world situation. They discovered that short-term outliers, which unexpectedly over- or underperformed, generating a factor they called “randomness.” Realizing this, they added threshold controls, which ended up greatly stabilizing their method.

“The mitigation of randomness yields two simple, but significant consequences,” Prof. Barra said. “When we lose, we tend to lose very little, and when we win, we tend to win considerably.”

Further enhancements will be needed, according to Prof. Barra, as other methods of automated trading already in use make markets more and more difficult to predict.

Reference: “Deep Learning and Time Series-to-Image Encoding for Financial Forecasting” by Silvio Barra, Salvatore Mario Carta, Andrea Corriga, Alessandro Sebastian Podda and Diego Reforgiato Recupero, May 2020, IEEE/CAA Journal of Automatica Sinica.
DOI: 10.1109/JAS.2020.1003132

5 Comments on "AI System – Using Neural Networks With Deep Learning – Beats Stock Market in Simulation"

  1. Zack Barkely | June 3, 2020 at 8:57 am | Reply

    The problem here is the stock market no longer functions to effectively invest in long term payoffs for innovation, but seeks short term gains which are often at odds with the former. The stock market mainly serves in redistributing wealth upward, where it is currently least deserved. Accelerating this process through AI could rapidly and exponentially destabilize our world. The most effective way to make a lot of money is by stealing resources and labor through war and slavery. If we give AI these kinds of incentives so a few people can make a lot more money than they deserve, it will be catastrophe. In affect, this is what already has occurred with Bezos and Mosk who have used autonomous agents as electronic slaves that acquire large amounts of capital (with our regulators apparently asleep at the wheel). If we create truly intelligent machines, this process could be put on steroids.

  2. Totally agree.

  3. Get a job, Zack.

  4. Link to paper is broken

  5. An AI myth is that it can predict the future. No one can predict the future, the best you can do is make educated decisions based on past behaviors. AI is no different, the difference is the speed and the amount of data used. Similarly, AI errors are fast and larger, particularly in very complex and/or poorly known processes, such as the stock market, as well as other events that involve human behavior with large subjective variables. I agree with Mr. Barkely with AI, we are creating biases and “alternative realities” that could bring disastrous results. AI is a tool and behind any tool, there must be a well-trained human being who uses multiple models and assesses risk.

Leave a comment

Email address is optional. If provided, your email will not be published or shared.