Artificial Intelligence In Finance and its Impact in Transforming the Industry


This article was written by Esther Hanon, a Financial Analyst at I Know First.

AI In Algorithmic Finance Demonstrate New Advances: 


  • Algorithms are being used every day to analyze human behavior and decision-making to analyze our thought processes which can help investors make profitable stock trades
  • Companies are using AI and algorithmic systems to analyze human behavior in the stock market to make accurate forecasts of stock trends
  • AI companies spot a business opportunity in space as innovation, massive investment, and lower costs are fueling a new commercial space race.
  • Geospatial Analytics increasingly becoming a booming industry, where satellites are being used to track everything from retail football to food production.

The Impacts of Financial Artificial Intelligence in Helping to Determine Stock Market Movements:

Contrary to popular belief, artificial intelligence (AI) is hardly a new topic. It has been around since 1956 when the seminal summer workshop was organized at Dartmouth College, New Hampshire, US.

Over the past few years, news articles and various companies have sprung up leading to the heavily floated term ‘Artificial Intelligence’ which has recently been circulated at an increasing rate. It’s one of those buzzwords that somehow finds its way in to every tech-related conversation. Even the least tech-savvy person has a vague notion of what it is. The problem is, some of the more tech-savvy person don’t have a much clearer notion of what it is either. The definition of AI ranges and has vague boundaries. Concepts range from artificial intelligence and neural networks in predicting the stock market, perhaps a smart home device, or the idea of a space innovation in tracking human consumption and usage.

As the name simply suggests, AI is the intelligence exhibited by machines. However, the inconsistencies stem from what one defines as intelligence. Currently, there are a variety of machine capabilities which researchers consider “artificial intelligence”. These include, successfully understanding human speech and competing at a high level in strategic game systems. Other examples include self-driving cars, intelligent routing in networks, and interpreting complex data.

Image result for artificial intelligence deep learning

[Source: Tofas Akademi]

Financial institutions are mostly interested in simulations and interpreting complex data. Banks and Fintech Wealth Management startups, like I Know First, use machine learning algorithms and AI machines to spot fluctuations in global stock markets. They then typically monitor transaction patterns by double-checking the algorithm results using human input, through backtesting. Over the recent years, banks and wealth-tech firms have since increased their capabilities with AI as technology has improved. They can now use artificial intelligence systems to organize operations, maintain bookkeeping, invest in stocks, and manage properties.

For years, artificial intelligence remained a subject of scholarly study or inspiration for techies, or perhaps avid science-fiction lovers. However, there has been a significant acceleration in recent years in many industries ands facets of society. AI has started to be implemented for real-world applications, including in business contexts.

Orbital Insight used AI to analyze satellite images and calculate how full these rooftop oil tanks are.


Artificial Intelligence Applications Today: 

Innovation, massive investment, and lower costs are fueling a new commercial space race. In case you’re wondering where else AI has been seeping into, an area that increasingly has been booming is geospatial analytics, an industry where satellites are used to track everything from retail, football, to food production.

According to an article written by CNN Money, companies working on the technology have obtained big money. Examples of companies include Orbital Insight which raised $50 million in funding last year, Descartes Labs with $30 million in funding and SpaceKnow with $4 million. One of the industry’s pioneers is James Crawford, who worked for NASA and Google before founding Orbital Insight in 2013. He noted that society is “seeing an explosion” in commercial satellites, producing all types of data, which “we have to do something with”. These firms can provide data on how much oil is being held in large land storage containers, or how many cars are in a Walmart parking lot, for example. This data has real economic value. Supermarket car counts, for example, are a predictor of sales. Artificial Intelligence allows firms to process sifting images of the whole world every day. Essentially, we are in the middle of two major revolutions: AI and commercial space.

Orbital Insight measured car parking around the 2016 Superbowl. 


A Global Data Set:

Typically when conducting market analytics, a data set is used to organize, sort, and ultimately press the information, many time using software programs, excel, or running them using algorithms and machine learning. A data set is a collection of data which most commonly corresponds to the contents of a single database or statistical matrix, where every column of the table represents a particular variable or input. This data, in finance, refers to data used to obtain insight into the investment process. These data sets are often used by hedge funds, banks, and other institutional investment professionals within an investment company. These alternative data sets are information that are often categorized as big data, which means that they are typically very large and complex and often cannot be handled by software traditionally used for storing and handling data, such as Microsoft Excel. I Know First, for example, uses data sets to collect, gather, and process market results to ultimately make predictions about the future movements of the market using AI, Machine-Learming, and Neural Networks.

Pic 2: Deep Learning and ANN

Just as I Know First uses data sets in the financial realm to make predictions about the market, other firms are doing the same, as seen with the firms making progress in AI Geospatial Analytics. Descartes Labs’  first application of its technology was building a model for US corn production. In general, cornfields are great for satellites in terms of image resolution. Cornfields are big, corn grows slowly and it doesn’t wander. Satellite imagery are used to locate fields, figure out what crops were growing in them, assess how healthy the crops were and then calculate likely production levels. Satellites are taking pictures of the whole world. That’s a global dataset. They are applying modern machine-learning techniques to that data and using it to better understand our planet.

How Can the Financial Markets be Predicted Using Algorithms?

Markets Are Complex Systems

Looking at the common fallacies about stock markets, we can see two major types of groups. The first group is connected to the classical economic theory, which claims that markets are 100% efficient, and as such, are unpredictable. Accordingly, trying to forecast the stock market is useless, as no stock can possibly be a better deal than another. Both of these stocks are efficient and everybody in the market has perfect information available to them. From our daily lives, it is obvious that this does not truly reflect reality. There are people who actually profit trading stocks, which should not be possible in this idealistic market of economic theories.

On the other hand, it is also true that stock markets are completely chaotic, which the other big group claims. Due to this, big trading houses such as Goldman Sachs are able to profit consistently, although in the chaotic market the profits and losses would always sum up to zero over a longer period of time. Where is the truth then? The complexity theory gives us an answer – markets are complex and chaotic systems and their behavior contains both a systemic and a random component. Therefore we can make a realistic stock market forecast, although it is precise only to a certain extent.

Complex chaotic systems are vulnerable to minor changes (butterfly effect applies) causing a big perturbation in the system pushing it far away from its equilibrium. Therefore, we are usually able to predict the behavior of such systems (such as the state of the atmosphere and the weather) with a small error over a short period of time. This occurs until the minor errors accumulate and the system of feedback loops moves the system in a different direction than the prediction models. Even in this limited way, creating realistic stock market forecasts is surely possible and gives us the prospect to understand how the market works and why big bubbles and big crashes happen.

Complexity in the Chaotic Theory – Combining Chaos and Patterns

As already mentioned, the complexity of a system is a result of either the complex structure of the system (i.e. involvement of lots of actors with different goals and strategies) and/or of its complex dynamics (i.e. with a lot of interdependencies and feedback loops between the system elements). Such complexity inevitably leads to chaos, when times with well-defined and predictable paths are interrupted with instability regimes where a minor perturbation can switch the future path between two opposite directions. It is important to note that the switch is not purely random, as the chaotic systems have memory and patterns tend to repeat.

Concerning the stock market, chaos is the result of the psychology of trading, which is never purely rational. People react with different emotional intensities to gains and losses tend to become biased by the latest news and subsequently are not able to quantify risks accurately. However, there are underlying principles, basic economic assumptions, telling us that people try to reach the highest returns with the lowest amount of risk. Looking at price trends of a stock, we can generally say that the prices jump from one level to another, creating a pattern as we can see in the image below. However, this cannot be seen at every time horizon. When we look too closely, on 1 day or even 1 month diagram, no patterns are apparent. Granularity matters and it is impossible to predict short-term movements of prices. With a longer time horizon, we can be far more successful, when we understand the underlying dynamics.

To learn more about this topic, click here.

Stock Price Showing Patterns in 5 Years Horizon

Stock price showing patterns in 5 years horizon

I Know First and their own ‘AI Data Set’:

I Know First predicts a growing universe of over 8,000 securities for the short, medium and long-term horizons daily by applying Artificial Intelligence and Machine Learning techniques to search for patterns and relationships in large sets of historical stock market data. Through its self-learning ability and flexible multi-layered neural networks structure, the algorithm is able to learn from, adapt to and evolve together with continuously changing markets. It offers an independent, objective and unique perspective on the financial markets and doesn’t rely on any human-derived assumptions or traditional theories and models that often do not hold (anymore).

The results of intense learning and prediction cycles are aggregated into two indicators per time frame: signal and predictability. While predictability indicator helps to identify and focus on the most predictable assets, the signal is used to define and rank the trades and is related to the magnitude of expected return. The applications of the algorithmic AI-based forecasts are multi-fold.

The scalability of the algorithmic predictive system allows I Know First to offer custom forecasting solutions to hedge funds and other financial institutions, so they can identify the best opportunities as discovered by the self-learning algorithm within the investment universe of their interest. Further, the solution can be used as a decision support system in form of an algorithmic screen integrated into client’s investment process in order to confirm or reject investment ideas before the execution.

Moreover, I Know First develops and back-tests systematic trading strategies which are used in partnerships with hedge funds and other asset managing entities. These strategies are rules-based and utilize algorithmic forecasting indicators mentioned above in order to rank and select the trades as well as times the execution. The type of strategies varies, including mean-reversion logic and more trend-focused approaches, all generating high positive alpha while keeping beta in the  0.3-0.8 range, yielding overall high risk-adjusted returns. The strategies can be used in partnership with I Know First to launch hedge funds, mutual funds or other investment vehicles.  I Know First’s AI-based algorithm, which incorporates multi-layered neural networks and genetic algorithms, allows us to model the market without human-derived assumptions. By doing so, our algorithm is able to achieve flexibility with regards to the model and evolve with the ever-changing markets. The algorithm continually learns and adapts based on its previous forecasts, and adapts to new conditions and features quickly.


Additionally, the design of the algorithm further enhances its capabilities to be able to make predictions in circumstances not observed before, as a result of its learning experience and intelligence. This is something one cannot achieve without AI technology. This maximizes the efficiency of employees when applied to financial institutions. Financial employees become more efficient when they have help from the I Know First algorithmic system. The algorithm is already in use among institutional investors; the product is used by research and analyst teams in hedge funds, banks, and family offices or by financial advisors. The efficiency of employees also leads to decrease in operating costs. Rather than employing multiple people to analyze the market, the algorithm does much of that for the company, so the company will cut down extensively on employee wages while retaining integral financial professionals.

logo1I Know First develops, back-tests and offers systematic trading strategies which are used in partnerships with hedge funds and other asset managing entities. These strategies are rules-based and utilize algorithmic forecasting indicators in order to rank and select the trades as well as times the execution. Here the final product is the trades recommendations for execution, depending on the investment strategy profile chosen. The type of strategies varies, including mean-reversion logic and more trend-focused approaches, all generating high positive alpha while keeping beta in the 0.3-0.8 range, yielding overall high risk-adjusted returns. The strategies can be used in partnership with I Know First to launch hedge funds, mutual funds or other investment vehicles.

Secondly, the two-fold business model puts I Know First in a unique position: offering custom and standardized algorithmic forecasts to a variety of clients (institutional and retail) and researching and developing systematic trading strategies for fund management purposes on a revenue-sharing basis. The business model proved itself and I Know First has earned clients’ trust for over four years now and is partnering with large financial institutions not only in Israel (asset manager) but also Europe (bank), United States (wealth management) and Japan (financial information provider).

The competitive advantages can be summarized as follows:

  • Innovative, independent and objective AI-based approach, separating it from traditional models and tools
  • Self-learning, adaptability and “general intelligence” characteristics, allowing to adapt to, evolve with and predict ever-changing financial markets
  • Unique predictability indicator, allowing to identify and focus on most predictable assets
  • Daily updated ranked forecasts for >8,000 assets, incorporating most recent market events
  • Scalable system, allowing to customize offerings to clients, enter new markets and create business opportunities
  • Providing solutions not only to large financial institutions but also empowering retail investors with AI technology applied to financial markets
  • Algorithmic trading ideas generator and decision support system as Cost-Benefit for clients & banks in the context of new regulations that aim to solve conflicts of interests, encourage transparency and to ban commissions payable in respect of investment advice and portfolio management (see e.g. MiFID-2 in the EU)
  • Furthermore, when applying traditional tools often too much subjectivity from the user is required. I Know First algorithmic forecasting technology offers a unique objective, adaptable and self-learning advisory system that is built without any human-derived assumptions and doesn’t include any subjective qualitative features.

To subscribe today click here.

I Know First Algorithm Heatmap Explanation:


This indicator represents the predicted movement direction/trend; not a percentage or specific target price. The signal strength indicates how much the current price deviates from what the system considers an equilibrium or “fair” price.

The signal strength is the absolute value of the current prediction of the system. The signal can have a positive (predicted increase), or negative (predicted decline) sign. The heat map is arranged according to the signal strength with strongest up signals at the top, while down signals are at the bottom. The table colors are indicative of the signal. Green corresponds to the positive signal and red indicates a negative signal. A deeper color means a stronger signal and a lighter color equals a weaker signal. The sign of the signal tells in which direction the asset price is expected to go (positive = to go up = Long, negative = to drop = Short position), the signal strength is related to the magnitude of the expected return and is used for ranking purposes of the investment opportunities.

An analogy with a spring: The signal strength is how much the spring is stretched. The higher is the tension the more it’ll move when the spring is released.


This measures the importance of the signal. The predictability is the historical correlation between the prediction and the actual market movement for that particular market. For each asset this indicator is recalculated daily. Theoretically, the predictability ranges from minus one to plus one. The higher this number is the more predictable the particular asset is. If you compare predictability for different time ranges, you’ll find that the longer time ranges have higher predictability. This means that longer-range signals are more important and tend to be more accurate.

Predictability is the actual fitness function being optimized every day and can be simplified explained as the correlation-based quality measure of the signal. This is a unique indicator of the I Know First algorithm. This allows users to separate and focus on the most predictable assets according to the algorithm. Ranging between -1 and 1, one should focus on predictability levels significantly above 0 in order to fill confident about/trust the signal.

To subscribe today and receive exclusive AI-based algorithmic predictions, click here.