Predicting Chaos: Story Behind One Of Israel’s Most Advanced Fintech AI Start-Ups-MAZZ Home
Artificial Intelligence is already having a transformative effect on many industries
The artificial intelligence technology seems virtually omnipresent at this point, and the rise of AI has been dramatic enough for some to call it the new electricity. And although some of the hype may be misplaced, the fact persists: the rise of AIs has already transformed whole industries.
And while that was happening, the financial sector was also taking note. Among the many boons of AI tech for finance is the practice called algorithmic trading: the idea that an advanced AI may be able to assist the investors by predicting the market dynamics with enough precision to make consistent profit. And while many advanced machine learning models developed for this purpose stay outside the reach of the general public, others are eager to make AI-driven trading available to a broader audience.
One of the leaders in this sphere is the Israel-based company with an ambitious name I Know First. With its powerful cloud-based AI capable of predicting the price dynamics for more than 10,000 financial instruments, including stock ideas, ETFs, world indices, commodities and currencies, it offers its forecasts to private and institutional investors alike. However, the story of its success began with something that did not necessarily have too much to do with finance or, more precisely, with one visionary’s research in chemistry.
The Origins: Patterns In Chaos
Currently a world-class expert on AI with around 20 years of experience under the belt, Dr. Lipa Roitman started off as a chemist. After graduating from the Novosibirsk State University in Russia with an MSc, he went on to complete his PhD at the Weizmann Institute of Science in Israel. Before delving into AI and startups, he worked for years as a chemist, focusing, among other things, on polymers and colloids. In his research, Dr. Roitman would often find himself working with chaotic systems complex dynamic systems that can be thrown off balance by a smallest event, with the causal link sometimes not directly obvious.
As he looked for trends and patterns in these systems, he began to notice a parallel with stock markets, huge comprised of thousands of individual stocks, their prices shooting up and down every now and then. And despite all the random noise, he felt it was still possible to identify trends in these systems, and even predict their behavior.
Dr. Roitman saw this as a good field for the application of the AI technology, which at the time was nascent. By that point, he had moved on from chemistry to entrepreneurship, living in the United States. In his basement in Ohio, he dreamt up a system that would utilize advanced statistical programming and historical and up-to-date stock market data to calculate the outlook for various financial instruments.
This vision came to life after he met Yaron Golgher, a seasoned expert in finance and consulting. Working together, with Dr. Roitman’s scientific prowess and Golgher’s experience with finance and investment, they were able to train a deep learning-based predictive algorithm that drew upon chaos theory and reinforcement learning. This was the beginning of their joint endeavor, a company they will call I Know First to appeal to those who want to be one step ahead of the market.
The I Know First Algorithm: Crystal Ball For Age Of High-Tech
The I Know First AI looks at the markets from a holistic perspective, trying to model the interplay between the fluctuations of different stocks and their dynamics. If one is going down, it could drag a whole cluster with it, but also bolster the positions of others, and the algorithm tries to model all that and pick up the best items for investment generating the highest returns.
Thanks to its reinforcement learning capacities, the abundance of time the AI has had to process the historic database at its disposal, covering 15 years of trading, as well as new market data coming in has helped it to greatly improve its performance. The new data is used for cross-validation of the models to avoid overfitting, or tailoring them to the available data to the degree that they are no longer able to deal with new inputs correctly.
One of the features of the algorithm is that it not only delivers the forecasts, but also offers a measure of confidence in the prediction. Ranging from -1 to 1, the predictability score is a Pearson correlation coefficient comparing the algorithm’s past predictions of the stock against the real changes in its price. This allows investors to act only on those signals that have proven to be highly predictable. The signals themselves are presented as a score demonstrating the respective performance of an asset against the rest of the assets on the forecast.
The Success: Onwards And Upwards
Fast-forward 20 years, what started off as a two-man project has now grown into a company with a global footprint and two offices in Tel Aviv. The company has won a multitude of awards, most recently, voted in as the Best International Startup at the Geneva WealthTech Forum on March 14th. The company was also featured as the one of the top fintech companies in Israel and also Top 3 Fintech Company in Europe in robo-advisory at the European FinTech Awards 2017.
The company can boast a long list of customers, including both private and institutional investors, such as banks and hedge funds, stretching across 70 countries. Much to the pride of its founders, I Know First has been successful enough to run as a bootstrap operation, without any need for outside investment.
The company is present on a multitude of markets, including North and South Americas, Europe and Asia. The list of assets that the algorithm is capable of working with is constantly growing, and the company’s ultimate ambition is, quite literally, to leave no financial tool on the planet unprocessed.
Press Release Distributed by The Express Wire
To view the original version on The Express Wire visit Predicting Chaos: Story Behind One Of Israelâs Most Advanced Fintech AI Start-Ups