Executive Summary

In this Forecast Evaluation Report, we will examine the performance of the forecasts generated by the I Know First AI Algorithm for the Forex market that we send to our customers on a daily basis. Our analysis covers time period from March 28, 2019 to May 19, 2019. We will start with an introduction to our asset picking and benchmarking methods, and then apply it to the currency pairs universe as covered by the I Know First’s “Currencies” package. We will then compare returns based on our algorithm with the benchmark performance over the same period. Below, we present our key takeaways from applying signal and volatility filters to pick the best performing currency pairs:

Currencies Highlights:

• Top 5 currency pairs had better returns in all short-term time horizons, providing an average return of 0.21% in the 2 day horizon which outperformed the benchmark by 950%.
• Top 5 currency pairs provided the highest return of 0.24% in 1 day.

Note that the above results were obtained as a result of evaluation conducted over the specific time period and using a sample approach of consecutive filtering by predictability and by signal indicators to give a general presentation of the forecast performance patterns for specific currency pairs. The following report provides extensive explanation on 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 short term and flexible forecasting for the currency market.

About the I Know First Algorithm

The I Know First self-learning algorithm analyzes, models, and predicts capital markets, including currencies, stocks, commodities, interest rates and bonds markets. 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 the trend. This helps the trader to decide which direction to trade, at what point to enter the trade, and when to exit. Since the model is 100% empirical, the results are based only on factual data, thereby avoiding any biases or emotions that may accompany human derived assumptions. The human factor is only involved 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.

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 that result. It is a Pearson correlation coefficient between past algorithmic performance and actual market movement. This is measured from -1 to 1.

You can find the detailed description of our heatmap here.

The Currencies Picking Method

The method in this evaluation is as follows:

We take the top X most predictable currencies universe exchange rates pairs, and from them we pick the top Y highest signals.

By doing so we focus on the most predictable assets on the one hand, while capturing the ones with the highest signal on the other.

For example, a top 30 predictability filter with a top 10 signal filter means that on each day we take only the 30 most predictable assets, and then we pick from them the top 10 assets with the highest absolute signals.

We use absolute signals since these strategies are long and short ones. If the signal is positive, then we buy and, if negative, we short.

The Performance Evaluation Method

We perform evaluations on the individual forecast level. It means that we calculate what would be the return of each forecast we have issued for each horizon in the testing period. Then, we take the average of those results by strategy 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 purchasing the asset based on our prediction and selling it exactly 1 month in the future.

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

Note that this evaluation does not take a set portfolio and follow it. This is a different evaluation method at the individual forecast level.

The Benchmarking Method

The theory behind our benchmarking method is the “Null hypothesis“, meaning buying every asset in the particular asset universe regardless of our I Know First indicators.

In comparison, only when our signals are of high signal strength and high predictability, then the particular currencies pairs should be bought (or shorted).

The ratio of our signals trading results to benchmark results indicates the quality of the system and our indicators.

Example: A benchmark for the 3 days horizon means buy on each day and sell exactly 3 business days afterwards. We then average the results to get the benchmark. This is to conduct an apples to apples comparison.

Currencies universe under consideration

In this report, we conduct testing for the 50 currencies pairs covered by I Know First in the “Currencies” package. This package includes the major worldwide traded currency pairs, such as USD/EUR, USD/GBP, etc.

Performance: Evaluating the predictability indicator

We conduct our research for the period from March 28, 2019 to May 19, 2019. Following the methodology as described in the previous sections, we start our analysis by computing the performance of the algorithm’s signals for time horizons ranging from 1 day to 4 days, without first considering the signal indicator. We applied filtering by the predictability indicator for 4 different levels to investigate its sole marginal contribution in terms of return, and observe how returns change as these different filters are applied. Afterwards, we calculated the returns for the same time horizons for the benchmark using the currencies universe and compare it against the performance of the filtered sets of assets. Our findings are summarized in the table (Table 1) below:

Table 1. Currencies Predictability Effect On Return

From the above table, we can observe that Top 30 assets filtered by predictability generally provided much better returns than the benchmark. Though the return on investment seems to be falling over the time horizon, returns based on predictability still generally outperform the benchmark significantly. The maximum performance was recorded for Top 30 currencies pairs at the 2 days horizon – 0.09%. After analysing the currencies’ predictability on return, we continue our study in order to identify whether the results could be improved in the case of Top 30 currencies pairs when we filter by signal indicators.

Performance: Evaluating the signal indicator

In this section, we will demonstrate how adding the signal indicator to our asset picking method improves the above performance even further. It is important to measure the performance of our strategy with respect to the benchmark, and for that we will apply the formula:

We further filtered the assets based on signal strength to the Top 30 assets, which were previously already filtered by predictability. The results of the testing showed that there is a significant positive marginal effect on the assets’ return, especially in the case of the 2 days investment horizon. We present our findings in the following table and charts.

Table 2. Currencies’ Signal Effect on Rate of Return and currencies’ Out-performance Delta with respect to the Benchmark Return Rate 

Figure 1. Rate of return of all categories of signals and the benchmark for 1 day horizon after Top 30 predictability filter and Top 10 signal filter

Figure 2. Rate of return of all categories of signals and the benchmark for 2 days horizon after Top 30 predictability filter and Top 10 signal filter

Figure 3. Rate of return of all categories of signals and the benchmark for 3 days horizon after Top 30 predictability filter and Top 10 signal filter

Figure 4. Rate of return of all categories of signals and the benchmark for 4 days horizon after Top 30 predictability filter and Top 10 signal filter

From the above set of charts, we can clearly see that if we apply signal strength filtering to the currencies universe, all subsets of the Top 30 predictability signals – namely, the Top 20, Top 10 and Top 5 signals – seem to immediately produce greater returns than the benchmark. We see that returns are immediate from Day 1 onward for all signal categories. Overall, the Top 5 signal category seems to be the best performing with its returns following a bell-shaped curve for this particular time period.

Although we observe that the returns of all categories actually drop for slightly longer time horizons, with 4 day returns being 0% for all signal categories, when we compare the rates of return after applying the algorithm from I Know First with benchmark returns, we see that the signals are actually very effective. In all cases, the Top 20, Top 10 and Top 5 signals perform just as well or much better than the benchmark. This is especially true for the Top 5 signals, which notably outperformed the benchmark by 950% after 2-days, and by 400% after 3-days. Though the trend as reflected from the benchmark seems to be a downward one, one can see that following the signals from the I Know First currencies packages presents opportunities for better returns. This seems to be especially true in very short-term periods, such as 2 days and 3 days time horizons. Market opportunities in the currency market hence seem to expire fast, and signals that are presented require quick action to maximise rates of return.

Conclusion

In this analysis, we demonstrated the out-performance of our forecasts for the currencies pairs from Currencies universe picked by I Know First’s AI Algorithm during the period from March 28, 2019 to May 19, 2019. Based on the presented observations we record significant out-performance of the Top 5 currencies pairs when our signal indicators are used as an investment criterion. As shown in the above diagram, the Top 5 currencies pairs filtered by signal yield significantly higher return than any other asset subset on all considered time horizons spanning from 1 day to 4 days. Thus, an investor who wants to critically improve the structure of his investments into Forex market within his portfolio can do so by simultaneously utilizing the I Know First predictability and signal indicators as criteria for identifying the best performing currency pairs.