Brazil Stock Market: 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 Brazil stock market forecasts for long and short positions which were sent daily to our customers. Our analysis covers the period from January 1st, 2018, to June 30th, 2020.

Brazil stock market
Chart 1: Performance comparison for Top 20, Top 10 and Top 5 long position signals by Daily Model vs Bovespa Index for short term horizons since January 1st, 2018 until June 30th, 2020
Brazil stock market
Chart 2: Performance comparison for Top 20, Top 10 and Top 5 long position signals by Daily Model vs Bovespa Index for long term horizons since January 1st, 2018 until June 30th, 2020
Brazil stock market
Chart 3: Performance comparison for Top 20, Top 10 and Top 5 long and short position signals by Daily Model vs Bovespa Index for short term horizons since January 1st, 2018 until June 30th, 2020
Brazil stock market
Chart 4: Performance comparison for Top 20, Top 10 and Top 5 long and short position signals by Daily Model vs Bovespa Index for long term horizons since January 1st, 2018 until June 30th, 2020

Brazil Stock Market Highlights

  • The Top 20, Top 10, and Top 5 signal groups generated by I Know First consistently outperformed Bovespa Index for almost all time horizons.
  • The Top 5 signal group outperformed the Bovespa by 16.23% using the 1 year time horizon.
  • All hit ratios for 7 day time horizon or longer are above 50%.
  • Using only long positions, every signal group for every time horizon outperformed Bovespa.
  • For long positions only, the top 5 signals with a 1 year time horizon outperformed the Bovespa Index by 21.07%.
  • Long position hit ratios for all time horizons longer than 3 days are above 50% and all 1 year forecast hit ratios are above 70%

About the I Know First Algorithm

/var/folders/f2/mdjhl92x4g1fqsjkf838n96r0000gn/T/com.microsoft.Word/WebArchiveCopyPasteTempFiles/image-12.png

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 Brazil Stock Market Forecasts: Brazilian Stocks Package

The Brazilian Stocks package is one of I Know First’s systematic trading tools. The package includes a daily prediction for Brazilian 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:

/var/folders/f2/mdjhl92x4g1fqsjkf838n96r0000gn/T/com.microsoft.Word/WebArchiveCopyPasteTempFiles/image-13.png

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:

S&P500

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: Bovespa Index

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

The Bovespa Index measures the stock performance of the Brazilian stock market. It is one of the most followed equity indices and is frequently used as the best indicator for the overall performance of Brazilian public companies, and the Brazilian market as a whole.

For each time horizon, we compare the Bovespa Index performance with the performance of our forecasts.

Performance Evaluation: Overview

In this report, we conduct testing for the Brazil stock market that I Know First covers by its algorithmic forecast. The period for evaluation and testing is from January 1st, 2018 to June 30th, 2020. During this period, we were providing our clients with daily forecasts for Brazilian stocks in short term and long term time horizons spanning from 3 days to 1 year which we evaluate in this report.

Brazilian Stocks: Long Position Evaluation

Table 1: Daily long position forecasts average performance vs Bovespa for time horizons from 3 days to 1 year since January 1st, 2018 until June 30th, 2020

For long positions only, our returns for every signal group and time horizon outperformed the Bovespa Index. The top 5 signal group significantly outperformed the benchmark for every time horizon. That group 1 year time horizon had a return of 35.10% while the Bovespa increased by 14.03%.

Table 2: Daily long position forecasts hit ratios for time horizons from 3 days to 1 year since January 1st, 2018 until June 30th, 2020

In addition to having positive returns, there were also consistent gains shown by almost every signal group and time horizon having a hit ratio over 50%. The longer the time horizon, the more the hit ratio increases. For the 1 year time horizon, every signal group had a hit ratio greater than 70%.

Brazilian Stocks: Long and Short Position Evaluation

Table 3: Daily long and short position forecasts average performance vs Bovespa for time horizons from 3 days to 1 year since January 1st, 2018 until June 30th, 2020

As seen in Table 3, almost all forecasts, other than the 3 month time horizon, had positive returns. In addition, every signal group for the 7 day, 14 day, and 1 year forecast outperformed the benchmark. The best performing group was the top 5 signals for 1 year time horizon. This group had a return of 30.26% while the Bovespa index rose by 14.03%.

Table 4: Daily long and short position forecasts hit ratios for time horizons from 3 days to 1 year since January 1st, 2018 until June 30th, 2020

Although the 3 month time horizon didn’t have positive returns, it is notable that their hit ratios were all 50% or greater. This shows that the prediction was correct more often then not, however, there were a few big losses posted, likely on short positions which is why we will further evaluate our long position results.

Conclusion

This evaluation report presented the performance of I Know First’s algorithm for the Brazil stock market forecasts from January 1st, 2018 to June 30th, 2020. It shows the average returns and hit ratios for all time horizons.

The I Know First algorithm has obtained better performance for both short term and long term time horizons. It succeeded in generating significant positive returns for every signal group and time horizon. It is important to note that almost every signal group across every time horizon gave a hit ratio greater than 50%, and in some cases over 70%, 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.