Top Japanese Stocks: Daily Forecast 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 the Japanese stocks for long and short positions (20 stocks) which were sent daily to our customers. Our analysis covers the period from January 1st, 2019, to June 22nd, 2020 and further analyzes the performance of the Japanese market since the beginning of the Coronavirus pandemic, February 22nd, 2020.

Chart 1: Performance comparison for Top 20, Top 10 and Top 5 signals by Daily Model vs Nikkei 225 for short term horizons since January 1st, 2019 until June 22nd, 2020
Chart 2: Performance comparison for Top 20, Top 10 and Top 5 signals by Daily Model vs S&P 500 for period since February 22nd, 2020 (Coronavirus) until June 22nd, 2020

Top Japanese Stocks Highlights

  • The Top 20, Top 10, and Top 5 signal groups generated by I Know First consistently outperformed Nikkei 225 Index for all three time horizons.
  • The Top 5 signal group outperformed the Nikkei 225 by 5.39% using the two-week time horizon.
  • Since the start of the Coronavirus, the Top 20, Top 10, and Top 5 signal groups generated by I Know First remained extremely profitable, while the Nikkei 225 declined.
  • Using the two-week time horizon, the top 5 signal group outperformed the Nikkei 225 by 10.89% since the start of the Coronavirus.
  • Every signal group generated by I Know First succeeded in outperforming Nikkei 225 both before and after the start of the Coronavirus pandemic.
  • Hit ratios for all time horizons are above 50% since the start of COVID-19.

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.

Evaluating Japanese Stock Forecasts: Japanese Stocks Package

Japanese Stocks Package is one of I Know First’s systematic trading tools. The package includes a daily prediction for a total of 20 Japanese stocks with bullish and bearish signals:

For the analysis we group the forecasts by absolute signals since these strategies are long and short. If the signal is positive, then we buy and if negative, we short.

The Stock Market Forecast 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 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 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.

The Benchmarking Method: Nikkei 225 Index

In order to evaluate our algorithm’s performance in comparison to the Japanese market, we used the Nikkei 225 index as a benchmark.

The Nikkei 225 measures the stock performance of 225 blue-chip companies that are on the Tokyo stock exchange. It is one of the most followed equity indices and is frequently used as the best indicator for the overall performance of Japanese public companies, and the Japanese market as a whole. Nikkei 225 is a capitalization-weighted index, the weight of each company in the index is determined based on its market cap divided by the aggregate market cap of all the Nikkei 225 companies.

For each time horizon, we compare the Nikkei 225 performance with the performance of our forecasts.

Performance Evaluation: Overview

In this report, we conduct testing for the Japanese stocks that I Know First covers by its algorithmic forecast. The period for evaluation and testing is from January 1st, 2019 to June 22nd, 2020. During this period, we were providing our clients with daily forecasts for Japanese stocks in short term time horizons spanning from 3 days to 14 days which we evaluate in this report.

Table 1: Daily forecasts average performance vs Nikkei 225 for time horizons from 3 days to 14 days since January 1st, 2019 until June 22nd, 2020

As can be seen by Table 1, our algorithm provided positive returns for all three time horizons while the Nikkei 225 declined. For all three time horizons, the Top 5 signal group had the best performance. The Top 10 and Top 20 signal groups had a comparable performance for the 3 day forecast, but the Top 10 signal performed better for the 7 day and 14 day time horizons. While the Nikkei 225 further declined as time went on, all signal groups performed better, given longer time horizons.

Table 2: Daily forecasts hit ratio for time horizons from 3 days to 14 days since January 1st, 2019 until June 22nd, 2020

According to Table 2, the 3 day forecast generated the best hit ratio. Each signal group for the 3 day forecast had a hit ratio above 50%. The 7 day and 14 day forecast had hit ratios of 50% or below for each signal group. Nevertheless, these forecasts still had average returns that outperformed the Nikkei 225 and the 3 day forecast.

Performance Evaluation: Coronavirus

Table 3: Daily forecasts average performance vs Nikkei 225 for time horizons from 3 days to 14 days since Coronavirus pandemic

As can be seen by Table 3, returns increased drastically during the Coronavirus while the Nikkei 225 declined. Since February 22nd, the top five signal group for the 14 day forecast has outperformed the Nikkei 225 by almost 11%. Every signal group for all three time horizons has significantly outperformed the benchmark index. Even though the Nikkei 225 has been extremely volatile since the beginning of the Coronavirus, the algorithms returns have consistently been outperforming the benchmark index significantly. As with Table 1, Table 3 shows that with each signal group, the returns increase. This shows that the algorithm gets progressively more accurate as it narrows down the best Japanese stocks to trade.

Table 4: Daily forecasts hit ratio for time period since Coronavirus pandemic

In addition to the algorithm generating higher returns, the hit ratio for each signal group has remained above 50%. The 3 day forecast generated the highest hit ratio, although the returns didn’t match that of the other time horizons. This is significant because although the returns weren’t as great, a higher number of those signals had positive returns. The top 20 signal group reported the highest hit ratio for all three time horizons, however, it is extremely encouraging that all three signal groups had a hit ratio over 50% for all three short term time horizons.


This evaluation report presented the performance of I Know First’s algorithm for the Top Japanese Stocks forecast from January 1st, 2019 to June 22nd, 2020. It shows the average returns and hit ratios for all short term time horizons, with further performance evaluation done on the turbulent period since the Coronavirus pandemic.

The I Know First algorithm has obtained better performance for short term horizons. It succeeded in outperforming the benchmark for all of them with only positive results. Even more so, it outperformed the index during the Coronavirus pandemic which saw the Nikkei 225 give negative returns. It is important to note that every signal group across every time horizon gave a hit ratio greater than 50% since the Coronavirus, showing consistent and reliable accuracy.  It is advisable for traders to rebalance their portfolio using the most updated forecasts sent by I Know First.

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.