Best Israeli Stocks: Daily Forecast Performance Evaluation Report

Executive Summary

In this stock market forecast evaluation report, we will examine the performance of the forecasts generated by the I Know First AI Algorithm for Israeli stocks which were daily sent to our customers. Our analysis covers the time period from January 23, 2019, to March 23, 2020.

israeli stocks
Chart 1: Performance comparison for All Signals, Top 20, Top 10 and Top 5 signals vs TA 125 Index
israeli stocks
Chart 2:  Hit ratio for Top 5, Top 10 and All Signals
israeli stocks TASE 125
Chart 3: TA 125 Index Price (January 23, 2019 – March 23, 2020)

Best Israeli Stocks Evaluation Highlights:

  • Amazing performance with an average return of 33.55% over 1 year
  • I Know First reached an accuracy of 81% over 3 months
  • Most of signal groups have hit ratios greater than or equal to 50%
  • The majority of signal groups generated by I Know First succeeded in outperforming TA 125 Index

The above results were obtained based on forecasts’ evaluation over the specific time period using a consecutive filtering approach – by predictability, then by signal, to give an overview of the forecasting capabilities of the algorithm for the specific stock universe.

About the I Know First Algorithm

The I Know First self-learning algorithm analyzes, models, and predicts the stock market. 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 the movement of the asset. 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 measured from -1 to 1.

You can find a detailed description of our heatmap here.

Israeli Stocks Forecasts 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.

Assessing Forecasts’ Accuracy – Hit Ratio Method

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

Using our Daily Forecast asset filtering, we predict the direction of the movement of different assets. Our predictions are then compared against actual movements of these assets within the same time horizon.

The hit ratio is then calculated as follows:

For instance, a 90% hit ratio for a top 30 predictability filter with a top 10 signal filter would imply that the algorithm correctly predicted the price movements of 9 out of 10 assets within this particular set of assets.

Israeli Stocks Picking Method

We rank the assets by predictability for long and short positions, and then we apply a set of signal-based filters: top 20, 10 and 5 assets. We use absolute signals since these the assessment is based on long and short ones.

For example, out of all Israeli assets, application of a top 10 signal filter means that on each day we take only the top 10 assets with the highest absolute signals.

Performance Evaluation – The Signal Indicator Effect

We utilize the signal indicator in our asset picking method to achieve the maximum forecast performance. It is important to measure it with respect to the benchmark, i.e. how the selected assets out-perform the benchmark, and for that, we will apply the formula:

The Benchmarking Method – TA 125

The TA-125 Index, typically referred to as the Tel Aviv 125 and formerly the TA-100 Index, is a stock market index of the 125 most highly capitalized companies listed on the Tel Aviv Stock Exchange (TASE). The index began on 1 January 1992 with a base level of 100. The highest value reached to date is 1247.92, in January 2011. In 2017, the index was expanded to include 125 instead of 100 Israeli stocks.

The index is maintained by the Tel Aviv Stock Exchange and is calculated in real-time during trading hours and published every 30 seconds.

Performance Evaluation – Overview

In this report, we conduct testing for Israeli stocks that I Know First cover by its algorithmic forecast. The period for evaluation and testing is from 23th January 2019 to 23th March 2020. During this period, we were providing our clients with daily forecasts and the time horizons which we evaluate in this report are 6 periods spanning from 3 days to 1 year.

Top Israeli Stock Results: Average Return and Hit Ratio

israeli stocks
Table 1: Average performance VS TA 125 Index

As can be seen in Table 1, by applying the predictability filter our algorithm provided almost just positive returns (only negative one). The TA 125 Index was beaten by all signal groups for all term horizons (except one for 30-day time horizon by all signals). We can notice that the best performances are over the longest term horizons (365 days, 90 days and except one for 30 days). A very high performance was observed for 365-day time horizon by the Top 5 Signal filtering, reaching returns of 33.55%. Overall, the performance from top 20, top 10 and top 5signals for 90-day and 365-day time horizons were considerable. Those results indicate that the signal effect on forecast return was strong and consistent.

israeli stocks
Table 2: Hit Ratio for daily forecast model

According to the table above, the majority of the hit ratios were greater than or equal to 50%. Generally, the accuracy was better for the longest term horizons (365 days, 90 days and except one for 30 days). Indeed, we can observe that the best hit ratios are 81% and 78%. They were reached by top 5 Signals respectively over 90-day and 365 horizons. Overall, the accuracy is consistent. Moreover, particularly for the long time horizons, we can notice that the hit ratios of top 5 signal were higher than top 10 signal ones, and top 10 ones than top 20 ones and top 20 ones than all signal ones. Therefore the signal ranking made by I Know First was reliable.

israeli stocks
Table 3: Outperformance for daily forecast model

Overall, the out-performances were very high. Nevertheless, some of these results are not representative due to a low performance of the benchmark average return like over the 30-day time horizon for instance.

Conclusion

This evaluation report presented the performance of I Know First’s algorithm for the Israeli stock picks from January 23th, 2019 to March 23th, 2020. It shows the average returns and hit ratios for all time horizons and there was no predictability filter applied on these signals.

The results of this analysis showed amazing average returns by the I Know First algorithm. Indeed, the algorithm achieved very high average returns: 33.55%, 16.97% and 14.69% over 90-day and 365-day horizons. It also succeeded to outperform almost on every time horizon TA-125 benchmark index. Moreover, the hit ratios were good in general and better over the longest term horizons with the best hit ratio was 81%.

During this volatile period, the performances (average return and hit ratio) were higher for the longest term horizons. And for these time horizons, I Know First made a consistent signal ranking. Thereby, we can conclude that we are able to provide very precise forecasts which can be especially useful for passive investments for individual investors, for instance. We look forward to new market data in the following months and will monitor the changes in performance trends that are going to be communicated to our investors and subscribers in the follow-up reports.