I Know First is an AI fintech company that provides state of the art self-learning AI based algorithmic forecasting solutions for the capital markets to uncover the best investment opportunities. The company provides daily investment forecasts based on an advanced, self-learning algorithm. The AI Algorithm was developed by Dr. Lipa Roitman, who will also be speaking at the summit, a scientist with over 20 years of research and experience in artificial intelligence (AI) and machine learning (ML) fields, who leads our Research & Development team to further develop and enhance the algorithm. The concept of the current algorithm has crystallized following years of prior research into the nature of chaotic systems. His unique R&D team consists of PhD’s and AI and Machine Learning experts, including IDF intelligence veterans and consults with Prof. Yakov Yakubov, a mathematician from Tel Aviv University.
At the AI in Finance Summit in New York this September 06 - 07, I will be discussing my work as CEO and Co-Founder of the company and explain the underlying technology of the algorithm. This is based on artificial intelligence, machine learning, and incorporates elements of artificial neural networks and genetic algorithms through which we analyze, model, and predict the stock market. The algorithm is adaptable, scalable, and features a Decision Support System (DSS) to optimize the information produced by the years of data inputted.
The algorithm generates daily market predictions for stocks, commodities, ETF’s, interest rates, currencies, and world indices for the short, medium and long-term time horizons.
We started in 2011 with a prototype of our self-learning algorithm running on a desktop computer and began our quest to predict the stock market by focusing on one market- the US stock market. Once our stock forecast algorithm could successfully make predictions for this market we began expanding one market at a time until we reached over 10,000 assets including stocks, commodities, interest rates, foreign currency, exchange-traded funds (ETFs), global indices, and more across over 30 countries. Moreover, our algorithm creates forecasts across varying time horizons ranging from 3 days to a year so that clients can tailor which predictions they use based on how long they intend to hold an asset.
We’ve also grown to a full-time team with offices at the Tel Aviv port. Our R&D team is led by Dr. Roitman and is made up of PhDs, experts in AI and machine learning, mathematicians, statisticians, engineers, veterans from IDF intelligence units, and more. I Know First now has clients in over 50 countries and makes predictions over 40 markets across the world and considered one of the Top fintech companies in Israel.
Is the market truly predictable?
When people think of the stock market, they often think that it is too random to be predictable. However, what people tend to be unaware of is that the stock is not truly random, but rather a chaotic system. Chaotic systems have positive and negative feedback mechanisms that give rise to the following components that allow future events to be predicted: stability, memory, gradual change, and sudden and drastic change, all occuring in irregular cycles that can be analyzed mathematically, and some of these could be predicted. Using AI, it is possible to create models of chaotic systems like the stock market which allows our algorithm to create forecasts. And that’s exactly what our algorithm does- it finds order in the chaos by building the relationships between assets.
We utilize a combination of advanced machine learning techniques in order to get the most accurate forecasts. We combine deep learning, reinforcement learning, supervised and unsupervised learning methods, artificial neural networks, and more in our forecasts and other AI based products. While our machine learning algorithm isn’t an end all to be all, it can be used as an investment decision support tool and portfolios that take advantage of our predictions consistently outperform the market.
The system takes a holistic approach to the market. Everything is related, global events affect the local ones, and vice versa, causing a ripple effect. The algorithm builds the complex relationships between the various assets in the financial market which it can then use to identify investment opportunities. To a human it is logical that if the price of oil goes up, then oil company stocks will go down. Without knowing anything about a company besides its stock ticker, the algorithm can deduce the relationship between assets.
I Know First isn’t the only company trying to predict the stock market, so what makes us different/sets us apart?
Since it is a self-learning algorithm anytime our algorithm receives new data, it adjusts the model accordingly. We also provide a predictability indicator to our clients and I think that’s one of the key things that sets us apart from other companies that utilize AI to predict the stock market. This allows those viewing our heatmaps to make decisions based on both the predicted direction of the stock and the historical correlation between the algorithm’s predictions and successes.
Another important thing to consider is that the majority of algorithms for the stock market have been built by banks and are not available to individuals. While we work with institutional clients such as banks, wealth management funds, hedge funds, family offices and more; we also have a variety of packages that individuals can subscribe to depending on what stocks they’d like to receive predictions for. Additionally, instead of only choosing to provide predictions over a single set time period, we send daily predictions from one day to a year to both institutional and retail clients before the markets open as a decision supporting tool. Moreover, we have packages based on fundamentals like P/E ratio to sector-based packages based on various investment universes such as the S&P 500, technology, small caps, or any particular sector a client may need.
In addition to our daily stock market forecasts, we have also developed systematic trading strategies and can help clients build personalized portfolios.
We also recently added a new feature for our institutional clients to ‘whiten the black box.’ Most neural networks are a black box that take in an input and return an output without showing the user where it is coming from it. Now, we can provide reports that include the components and weight of each factor that makes up a prediction. Moreover, this peek into the black box also allows us to conduct ‘what-if’ scenarios and see potential outputs based on varying inputs. These fact that clients can understand where our predictions are coming from only solidify their confidence in using the forecasts as a trading support tool.
Now that we've conquered daily forecasts for over 10,000 assets, what’s next?
We’re still building momentum and can’t wait to see what the future holds. While 10,000 is a lot, we one day hope to be able to predict every single tradable asset in the world. We’ve been expanding into new markets such as in South America and Asia and are beginning to build our presence in these countries.
We currently have a lot of other new projects in the works too that we’re super excited about. We’re in the midst of creating new algorithms that can forecast liquidity, quantify uncertainty of stocks, and intraday predictions. These will all be support tools we will provide our subscribers to help with their trading decisions. We also recently received an investment advisor certification and plan to offer an AI based robo-advisor that will optimize each client’s portfolios and are in the process of creating a hedge fund.
We are also beginning to expand into other industries such as healthcare. We recently partnered with KST Medical Group and will being adapting our algorithm to predict cardiovascular diseases and events in the human body, which is another type of chaotic system.
Joining Yaron at the AI in Finance Summit in September is Uday Singh, Head of Process Automation and Robotics, Credit Suisse, Éric Charton, Senior AI Director, National Bank of Canada, Anton Prokopyev, Data Scientist, The World Bank and many other experts who will cover topics such as Insurance, Investment, FinTech, Financial Compliance, Financial Forecasting and more.