Executive Summary

In this forecast evaluation report, we will examine the performance of the forecasts generated by the I Know First AI Algorithm for Bitcoin currency pairs with time horizons ranging from 3 days to 3 months, which were delivered daily to our clients. Our analysis covers the time period from 1 January 2019 to 25 June 2019. Below, we present our key takeaways from applying our algorithm to determine the predicted direction in the given time horizon for Bitcoin currency pairs:

Bitcoin Currency Pairs Highlights:

• The best returns were obtained in the 1-month and 3-months time horizons, providing an average return of 77.68% in the 3-months time horizon.
• The best hit ratios were similarly obtained for the 1-month and 3-months time horizons, with the best hit ratio being 93% for the 3-months time horizon.

Note that the above results were obtained as a result of an evaluation conducted over the specific time period to give a general presentation of the forecast performance patterns for Bitcoin currency pairs. 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 is a new I Know First evaluation series illustrating the ability to provide successful long term and flexible forecasting for Bitcoin currency pairs.

About the I Know First Algorithm

The I Know First self-learning algorithm analyzes, models, and predicts the capital market, 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 is 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.

Our algorithm provides two independent indicators for each asset – signal and predictability.

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

The predictability indicates our confidence in the signal. The predictability is a Pearson correlation coefficient relating past algorithmic performance and actual market movement, measured from -1 to 1.

You can find a detailed description of our heatmap here.

The Performance Evaluation Method

We perform evaluations on the individual forecast level. This means that we calculate the return of each forecast we have issued for each horizon in the testing period. We then take the average of those results based on our positions on different currencies and forecast horizon.

For example, to evaluate the performance of our 1-month forecasts, we calculate the return of each trade by using this formula:

This simulates a client buying Bitcoin currency pairs on the day we issue our prediction and selling it exactly 1 month in the future from that day.

We iterate this calculation for all trading days in the analysed period and average the results.

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 Bitcoin currency pairs using our algorithm. Our predictions are then compared against their actual price movements within the same time horizon.

The hit ratio is then calculated as follows:

For instance, a 100% hit ratio would imply that the algorithm correctly predicted the price movements of all assets within the Bitcoin package.

Universe Under Consideration: Bitcoin

In this report, we conduct testing for Bitcoin currency pairs, which is covered by I Know First in the “Bitcoin” package. The Bitcoin Package is designed for investors and analysts who need predictions for the best cryptocurrencies to buy, in particular, for Bitcoin. It includes predictions with bullish and bearish signals and indicates the predicted direction in the given time horizon for the cryptocurrencies.

Performance Evaluation: Evaluating the Rate of Returns

We conduct our research for the period from 1 January 2019 to 25 June 2019. Following the methodology from the previous sections, we start our analysis by computing the performance of the algorithm’s signals for time horizons ranging from 3 days to 3 months. 

From the above table, we can observe that the return on investment from Bitcoin currency pairs is generally increasing over the time horizon. Right from the onset, for the short-term time horizon, a positive return has already been recorded, as seen by the 1.28% return for the 3-day time horizon. The maximum performance was recorded at the 3 months horizon – 77.68%. Similarly, we also observe double-digit returns for the 1 month time horizon, with returns of 20.67%.

Performance Evaluation: Evaluating the Hit Ratio

The aggregated hit ratio is obtained by considering the accuracy of the algorithm for each time horizon within the given time period. For instance, for the 3 days time horizon, all possible consecutive 3-day periods are considered from 1 January 2019 to 25 June 2019. The actual price movement of assets within the Bitcoin package is compared with our algorithm’s forecast. A 100% hit ratio would imply that the algorithm had correctly predicted all the Bitcoin currency pairs’ price movements in this period. We then average all figures over the number of possible consecutive time-periods to obtain the hit ratio effect figures.

As seen from the table above, we see that the algorithm has been extremely effective in determining the price movement of Bitcoin currency pairs. The best figure is for the 3-months time horizon, where the algorithm predicted 93% of price movements of Bitcoin currency pairs correctly. We see similar excellent results for other time horizons as well, with the accuracy of forecasts being at least 59% for all time horizons.

Conclusion

In this analysis, we demonstrated the out-performance of our forecasts for Bitcoin currency pairs-related, which was detected by I Know First’s AI Algorithm during the period from 1 January 2019 to 25 June 2019. Based on the presented observations, we record significant performance of I Know First forecasts for Bitcoin currency pairs for longer time horizons, as well as greater certainty of our forecasts over longer time horizons in terms of hit ratio. Thus, an investor who wants to add Bitcoin currency position to improve the structure of his investments within his portfolio can do so by utilizing I Know First’s forecasts to foresee price movements of Bitcoin currency pairs over different time horizons.