Big Data Systems

We have designed algorithmic trading systems that operate in derivatives markets in an unattended way, according to the predictions generated by the AI Big Data Models. The systems are available through Tading Motion platform:

Continuous Big Data Algortihmic Trading Systems:

Following the paper "Señales de inversión basadas en un índice de aversión al riesgo" written by Professor Dr. Raúl Gómez Martínez, published in 2013 by the IEDEE magazine, the volume of searches carried out in Google on economic-financial terms has explanatory and predictive capacity on the evolution of the markets. Since 2004, in which Google began to publish these statistics, it is observed that bear markets implies higher searches of terms such as crash, recession or short selling, while bullish markets implies searches on financial products . Bearing this in mind, in InvestMood we have created big data algorithmic trading systems that open long or short positions based on an AI model in which the predictors are those volumes of searches while the target is market trend (up/low). The models issue their predictions on a weekly or monthly basis:

Google Trends Weekly Systems: These systems train their AI models every Sunday, using a 5-year history of weekly Google search statistics of dozens of economic-financial topics. The system maintains a long or short position until there is a new prediction in the opposite direction or until the position is closed by trailing stop loss and take profit.

Google Trends Monthly Systems: On the first day of each month the models are trained with all the history available since 2004 and the prediction is released for the month. The system remains continuously open long or short according to the prediction obtained.

Intraday Big Data Algorithmic Trading Systems:

The intraday systems of InvestMood analyze news at night and qualify it as good, bad or neutral using natural language processing algorithms. With this information, artificial intelligence models are created that daily generates a prediction about the trend of the index the next session. Based on the probability offered by the model, these systems are left out of the market if the probability is low or they open long or short position, keeping their position open until the closing of the market or until the position closes by stop loss and take profit.

Investors' Mood Daily Trend (Long learning)
: Since November 2015, this Big Data Algorithmic trading system traces any communication that mentions the Ibex on Twitter, radio, television and press, and qualifies it. using these precitors, an AI model is created on the trend of the Ibex in the next trading session, up or down. The system is available on Trading Motion platform in two versions:
  1. Investors' Mood Daily Trend: Opens position everyday.
  2. Investors' Mood Daily Trend Low Risk: Opens position if the AI model prbability is higher than 75%.
Investors' Mood Daily Trend (Short learning): For this system, the AI model has used a learning period of only 6 months, neglecting the previous historical information. With this, it intends to be more agile (it enters the market if the probability is higher than 80%) and adapt more quickly to the sensations of the market.
  1. IA 6M Learning Ibex Mood:
Big Data MiniIbex Trend (combinación de sistemas): This big data trading system operates with the future of the MiniIbex so it only requires a daily guarantee of only  200 €. The algorithm that opens position has been developed combining the previous systems, it operates whenever the long and short training models coincide in their prediction with a probability higher than 70%. You can see the evolution of this model in:

Combined strategies:

The Google Trends Swing NQ algorithmic trading system is the outcome of more than three years of observation and research in Behvioral Finance, Artificial Intelligence and Machine Learning. Throughout this time we have observed that when all our AI models on American index point in the same direction, the success rates are better. On the other hand, the best option when they disagree is to be out of the market. Therefore, this system opens long and short positions in the Mini Nasdaq future if ​​at least 5 of the 6 models point in the same direction, otherwise the system remains out of the market. It is also optimized with a 2% StopLoss and a 7% TakeProfit. This system is available in:

The big data system of algorithmic trading Google Trends Weekly RTY generates its predictions about the trend (up / down) of the Russell index, over the next week, from the combination of 7 artificial intelligence models on the weekly and monthly trend of the main American indices (Dow Jones, Nasdaq, S&P 500 and Russell). You can access the system in: