Breaking News

The deep learning predictive AI algorithm developed by I Know First, a Fintech company that provides state of the art self-learning AI-based algorithmic stock market forecast solutions to uncover the best investment opportunities, has shown an accuracy of up to 95% in its predictions for Facebook (FB). That is according to aFacebook stock forecastevaluation report published by the company on August 25, 2019. The algorithm has demonstrated a higher accuracy rate for longer-term forecasts, as is often the case for predictive AI.

Facebook stock forecast hit ratio

“We provide AI-based forecasts for different time horizons. Machine learning algorithms do better on longer time horizons: the longer the time period, the greater the statistical significance and the greater the accuracy.” said I Know First CEO Yaron Golgher. “The algorithm is able to identify the trend, and to filter out the background noise. The longest forecast is for a year, but we also have a forecast for three month, and even for three days.“

Previously, the company also released itsApple stock forecastandSandP 500 and Nasdaqevaluation reports, which also revealed a high accuracy rate.

“The accuracy varies for different assets. Some asset are more predictable, some less so. The customer is receiving forecasts on a daily basis along with the latest investment opportunities, and knows this predictability indicator in advance. For example, Facebook stock is more predictable than Snapchat. In general, a predictions success rate above 51% can allow one to make gains even on fully-automated short-termalgorithmic tradingas long as the portfolio is diversified enough,” CEO Golgher said.

Facebook Stock Forecast Overview

The Facebook stock forecast evaluation report covers the predictions for FB stock delivered by the I Know First AI algorithm in the period from January 1st to July 9th, 2019. The review period saw FB go on a gradual climb from $135 to around $200, bouncing back every now and then on the back of US-China tensions and various controversies regarding Facebook’s privacy and other policies.

Facebook Stock Price Movements

Assessing the accuracy rates for forecasts ranging from 3 days to 3 months, the evaluation report covers most of the time horizons that the I Know First AI delivers predictions for. The short-term accuracy stood at around 60%, reflecting the increased volatility that FB was shaken by, but the 1-month and 3-months predictions demonstrated a significant increase in accuracy, guaranteeing the company’s clients the highest degree of certainty.

The exact hit ratio for each of the time horizons can be found in the sheet below.

Time Horizon 3 days 1 week 2 weeks 1 month 3 months

FB

58%

59%

64%

81%

95%

Facebook Inc. is a brainchild of Mark Zuckerberg and his Harvard roommates. A titan among American high-tech companies, it operates a variety of social media platforms; Facebook, its eponymous flagship social network service, boasts world’s highest number of users, which currently stands at around 2.23 bln. The company’s stock is immensely popular with international investors and is seen as one of the top blue-chip assets to pick.

The I Know First AI-Based Stock Market Forecast

The deep learning stock market forecast AI algorithm developed by I Know First has been trained on a dataset covering 15 years of trading. Deep learning is a term reserved for more complex artificial neural networks, ones in which the input data goes through a whole lot of transformations before the AI algorithm gives the appropriate output. The algorithm is given new trading data to process every day, making sure its output reflects the up-to-date state of the market.

The stock market forecast AI algorithm takes a holistic approach to the market, viewing it as a chaotic dynamic system, in other words, one highly sensitive to the initial conditions, where a seemingly small event can have tremendous repercussions. In doing so, it draws on the chaos theory to make sure that its models reflect this statistical disposition.

The algorithm also incorporates elements of genetic coding, keeping track of its own successes and failures and re-configuring its models if necessary. This ensures that the accuracy of its predictions goes up with every new iteration and helps it adapt to new market conditions, including periods of volatility and uncertainty like the one that the world is currently going through.

This design effectively eliminates any human bias in the system: every stock market forecast delivered is purely empirical in nature, as they are based on objective qualitative data and advanced statistical computations. The AI algorithm does not read the news, instead keeping track of the trends and feedback loops in the data, and is not prone to emotions that can sometimes mean downfall even for an experienced trader.

The forecasts are delivered as an easy to interpret heatmap, which includes two numerical indicators, signal and predictability. The former indicates if a given asset is expected to go up or down, while the latter demonstrates how good of a job the algorithm has been doing in its past predictions for this specific asset. Picking out the assets with the best indicators allows the investors to profit with the highest consistency, while keeping the risks at bay.

Stock Market forecast example

The AI algorithm delivers forecasts for over 10,500 assets, including stocks, ETFs, currency pairs and interest rates. Its predictions cover a wide range of time horizons, varying from 3 to 365 days, which allows it to be a worthy assistant in making decisions both on short-term trading and on long-term investment.

I Know First Predictive AlgorithmThe AI Algorithm was developed by Dr. Lipa Roitman, a scientist with over 20 years of research and experience in artificial intelligence (AI) and machine learning (ML) fields, who leads our Research and Development team to further develop and enhance the algorithm. Dr. Lipa Roitman is an RandD Chemist with a long record in computer modeling of processes, product development and process development. The concept of the current algorithm has crystallized following years of prior research into the nature of chaotic systems. His unique RandD team consists of PhD’s and AI and Machine Learning experts, including IDF intelligence veteransand consults withProf. Yakov Yakubov, a mathematician from Tel Aviv University.