S&P 500 Futures Forecast Performance vs S&P 500 Index – November 2019

S&P 500 Futures Executive Summary

In this forecast evaluation report, we examine the performance of the I Know First algorithmic forecasts for CME_SP1 futures contract and SPY ETF, which are based on S&P 500 index. The report covers predictions generated using the Regular model with time horizons ranging from 3 days to 3 months and additionally we are showing the performance of our Short-term model with time horizons ranging from 1 day to 6 days, available for institutional clients. Our analysis covers the time period from October 1st, 2018 to November 3rd, 2019. Below, we present our key takeaways for checking hit ratios of our stock market predictions.


  • 87% hit ratio for 1-year forecasting horizon when predicting CME_SP1 futures contract using Regular model
  • 74% hit ratio for 4-days forecasting time frame with CME_SP1 predictions using Short-term model
  • 92% hit ratio for 1-year forecasting periods for SPY ETF using Regular model

Note that the above results were obtained as a result of an evaluation conducted over the specific time period to give a presentation for the above mentioned assets’ movements. The following report provides an extensive explanation of our methodology and detailed analysis of the performance metrics that we obtained during the evaluation. This report continues I Know First evaluation series illustrating the ability to provide successful forecast on the S&P 500 Index and related ETF – SPY.

About the I Know First Algorithm

stock market predictions

The I Know First self-learning algorithm analyses, models, and provides stock market predictions for the capital markets, including stocks, bonds, currencies, commodities and interest rates. The algorithm is based on Artificial Intelligence (AI) and Machine Learning (ML) and incorporates elements of Artificial Neural Networks and Genetic Algorithms.

The system outputs the predicted trend as a number, positive or negative, along with a wave chart that predicts how the waves will overlap with the predicted trend. Consequently, the trader can decide which direction to trade, when to enter the trade, and when to exit the trade. The model is 100% empirical, based only on factual data, thereby avoiding any biases or emotions that may accompany human assumptions. I Know First’s model only involves the human factor in building the mathematical framework and providing the initial set of inputs and outputs to the system. The algorithm produces a forecast with a signal and a predictability indicator. The signal is the number in the middle of the box. The predictability is the number at the bottom of the box. At the top, a specific asset is identified. This format is consistent across all predictions.

stock market predictions
Forecast example

Our algorithm provides two independent indicators for the index – signal and predictability.

The signal is the predicted strength and direction of movement of the index. This is measured from –inf to +inf.

The predictability indicates our confidence in the signal. The predictability is a Pearson correlation coefficient relating to past algorithmic performance and actual market movement, measured from -1 to 1. You can find a detailed description of our heatmap here.

The Hit Ratio Calculation

The hit ratio helps us to identify the accuracy of our algorithm’s predictions.

We predict the direction of movement of an asset using our algorithm. Our predictions are then compared against actual movements of the S&P 500 within the same time horizon.

The hit ratio is then calculated as follows:

S&P 500 Index Composition

When thinking of index funds as benchmarks for the whole economy, many experts tend to gravitate towards checking the S&P 500. This prominent index, followed by millions throughout the globe, has historically shined a light on the movements in the stock market. What the index does, in essence, is choosing the 500 largest publicly traded companies by order of market capitalization and produces a quarterly list of corporations to be tracked. It is clear that any preemptive indication of how those shares appreciate or depreciate could be a powerful and highly profitable tool for investors. As for the CME_SP1 and SPY being the futures contract and an ETF, respectively, they are used as a common investment vehicle for wide range of investors due to the nature of their underlying asset, while also being a benchmark in respective futures and ETF markets.

Evaluating Long Term Model and Short Term Model Hit Ratios

The CME_SP1 and SPY forecasts are generated by the I Know First AI Algorithm for the long-term model which covers time horizons ranging from 3 days to 1 year and it’s available for institutions and individual investors. Additionally, we are generating AI predictions for the short-term model which covers time horizons ranging from 1 day to 6 days. This model is available only for institutional clients. The algorithm generates predictions independently for both models and for each time horizon.

Based on the above results, one can see that both models can consistently predict the CME_SP1 futures contracts, as well as SPY ETF, throughout various forecasting time frames. The hit ratio shows consistent improving trend for both assets in case of Regular model, reaching its peak at 1-year frame – 86.96% and 91.67% for CME_SP1 and SPY, respectively. As for the Short-term model, the general trend is positive and hit ratio stay above 50% almost across all horizons for both assets, and even for S&P 500 as benchmark. One of the major results is that the Short-term model has higher hit ratio for 3 days and 6 days horizons when compared to analogical results or Regular model for 3 days and 7 days, respectively. We see that Short-term model is able to significantly improve hit ratio when applied together with Regular model’s predictions. Specifically, for 3 days the improvement from using Short-term model is around 17% when compared to the Regular model, and for a week’s time horizons it is around 11%. Finally, the Short-term model showed its maximum performance in terms of hit ratio on 4-days horizon reaching extraordinary 73.96% and 71.91% for CME_SP1 and SPY, respectively. This result is extremely important as 4-days forecasts are the most universal and demanded by financial industry and wide range of traders and investors. These 2 models allow our investors to have a safer outlook for long and short term when investing despite these volatile time periods.


All in all, we at I Know First have a mission to provide our clients with the best information about the future. By sharpening our abilities to predict the S&P 500 and its derivative assets like CME_SP1 and SPY using our proprietary AI predictive algorithm, we provide our clients with increasing confidence that their investment will be safer and profitable. Within the bounds of certainty, we have consistently been able to find that we can predict the CME_SP1 and SPY movements with average 60% to 65% hit ratio in long and short time horizons. The peak for the Regularterm model is the 91.67% (SPY) and 86.96%(CME_SP1) hit ratio over the 1-year time horizon. Finally, we have a 73.96% and 71.91% hit ratio over the 4-days time horizon for the Short-term model, providing accurate predictions for short term investors.