Big Data
iStock

Decentralised analytics company Cindicator has undertaken a pilot project with the Moscow Stock Exchange, which showed the platform was able to drive an estimated 47% yield per annum for an experimental investment portfolio.

Cindictor, which recently raised $500,000 (£386,000) in seed investment, forecasts financial case outcomes combining data from 15,000 non-professional analysts and AI mechanics, to provide hedge funds and institutional investors with precise forecasts.

More from IBTimes UK

The pilot project saw a pool of 863 independent non-professional analysts' predicted price points for four futures daily. Based on answers to 56 questions, the platform powered around 100 deals, more than 80% of which turned out profitable. In 15 days, a model portfolio increased by 2.81% in value, which equals a 47% yield per annum. Interestingly, if the robot considered only the forecasts by the most accurate analyst, the profit would have been much lower, said a statement.

The platform combines collective human intelligence (trading strategies, human forecasts and buy/sell signals) with artificial intelligence ( machine learning model that integrates cleaning, clustering methods, linear regressions, Bayesian models, xgboost on decisive trees, genetic algorithms and neural networks) to increase the accuracy of financial forecasts.

Motivated financially and professionally, thousands of analysts generate forecasts daily. They answer questions about price levels of different financial assets, macroeconomic indexes and events. Machine learning models dynamically calculate weights for each forecaster, identify stable systematics in their errors, calculate corrections, eliminate noise and generate final predictions and trading signals.

Mike Brusov, CEO of Cindicator, said: "Financial markets depend on predicting the future. At what price and when to buy Facebook shares, Brent crude oil, the US dollar, or Bitcoin? In 2015, traders spent over $50bn on financial market data, with $4bn spent on predictive analytics. By 2020 this figure will increase approximately six-fold. Combining crowd intelligence with machine learning, Hybrid Intelligence can provide the market with unprecedented forecasting accuracy."

Examples of typical forecast questions put to Cindicator's Hybrid Intelligence on 1 September included the following:

  • Estonia has proposed to launch its own state-backed cryptocurrency, called "estcoin". The launch would make Estonia the first country with an Initial Coin Offering (ICO). Will Estonia launch its own cryptocurrency before 1 April 2018?
  • Germany is set to hold its federal election on 24 September. Polls currently show that Merkel's Christian Democratic Union / Christian Social Union (CDU/CSU) will be the largest party. Will CDU/CSU gain at least 40% of the seats in the Bundestag?
  • The next ECB meeting is scheduled on 7 September. The European Central Bank may reshape its quantitative easing package. Will the ECB cut the monthly pace of purchases at 7 September meeting?
  • Tesla's CEO Elon Musk promised to install the 100-megawatt lithium ion battery in South Australia within 100 days of the signing of the grid interconnection agreement, or it would be free for the SA government. Will Tesla build the battery in 100 days if the agreement is signed?

And the answers: Estonia will launch its own cryptocurrency before April 1, 2018 with 66% probability; CDU/CSU will gain at least 40% of the seats in the Bundestag with 68% probability; ECB will cut the monthly pace of purchases at September 7 meeting with 53% probability; and Tesla will build the battery in 100 days if the agreement is signed with the 81% probability

Newsweek's AI and Data Science in Capital Markets conference on December 6-7 in New York is the most important gathering of experts in Artificial Intelligence and Machine Learning in trading. Join us for two days of talks, workshops and networking sessions with key industry players.