Executive Summary:

In this analysis, we will evaluate the performance of the market forecasts generated by the I Know First AI Algorithm, specifically for the Retail Stocks Package. These results were observed for signals and predictability values of the Retail Stocks package delivered to our clients for the period of April 2020 to June 2021. The returns distribution for the Retail Stock are discussed below:

The Retail Stocks Forecast Highlights:

• The best return was generated by the Top 5 Signal index on the 1 year time period at 140.64%.  
• The Hit Ratio was more than 60% for all long term horizons.
• Even during uncertain pandemic times, I Know First has outperformed the S&P500 for all signals except for the 3 day forecast.
• On 14-days short term horizon, I Know First’s Retail Stocks forecasts have outperformed S&P 500 by 2.25% .

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.

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. 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.

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. Then, we take the average of those results by forecast horizon.

For example, 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. 

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 the actual movements of these assets within the same time horizon.

The hit ratio is then calculated as follows:

A 90% hit ratio for predictability implies that the algorithm correctly predicted the movements of 9 out of 10 assets.

The Benchmarking Method using S&P 500

In order to evaluate our algorithm’s performance, we used the S&P 500 index as a benchmark. The S&P 500 measures the stock performance of 500 of the U.S’ largest publicly traded companies. It is one of the most followed equity indices and is frequently used as the best gauge of large-cap US equities. The S&P 500 is often used as a benchmark for the performance of US publicly traded companies, and the US market as a whole. The S&P 500 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 S&P 500 companies.

For each time horizon, we compare the S&P 500 performance with the performance of our forecasts.

COVID Impact on Retail Stocks and the S&P 500

Retail stocks were hugely impacted by the COVID pandemic as the economy went through a long period of economic downturn, and many stores and businesses lost customers and revenue. According to the Investopedia report, the retail industry dropped almost 11% below the S&P 500 index. At the same time, according to the US Census Bureau, clothing sales dropped a gigantic 89.3% by April of 2020 alone, making it one the biggest drops in economic history. 

Looking at the below graph, we can see that the S&P 500 XFT Retail ETF fund has begun to recover after a significant drop from February 2020 to April 2020, and throughout our 7 month evaluation period, we are able to see an increasing trend in the S&P 500 index as the retail market is recovering from the COVID-19 pandemic.

Performance Evaluation Overview

In this report, we conduct testing for the Retail Stocks package predictions that the I Know First AI algorithm generates daily and which were distributed to I Know First clients. The period for evaluation is from April 2020 to June 2021 this report covers six forecasting time horizons spanning from 3 days to 1 year.

Retail Stocks and Signal Indicators

This section will explore how the signal indicators helped us to improve our strategies for successfully picking stocks.

From the table above, it is clear that the average potential returns resulting from the stock price predictions generated by the I Know First algorithm are greater than S&P 500’. We found that by using the signal indicators as selection criteria for filtering for the best stock picks and we had greater returns on all forecasting horizons. Most notably, we saw the highest return for the 1-year horizon at 140.64% which greatly exceeds the S&P 500 benchmark return of 43.93, by 96.71%.

From the above charts, it is evident that as the forecasting horizon expands, the average returns tend to become higher. Above all, the returns for the longer horizons provided premiums above the S&P 500 average by a larger percentage comparably to the shorter-term horizon in the same signal group. Ultimately, I Know First algorithm shows the highest average return for the 1-year forecast as 79.56% for the Top 20 Signals which exceeds the S&P 500 index by 35.63%; 125.37% for the Top 10 Signals which is greater than the S&P by 81.44%, and 140.64% which is greater than the S&P index by 96.71%. While I Know First has a lower return than the S&P 500 in the 3 day period, one can see that as the horizon gets longer I Know First success increases compared to the S&P 500. In the 14-days’ period, the AI Algorithm was able to generate the highest return of 3.88% for the Top 5 Signals which exceeds the S&P 500 index of 1.63%; 3.05% for the Top 10 Signals which outperforms the S&P 500 index of 1.63% by  1.42% and; 2.32% for the Top 20 Signal indicator which exceeds the S&P 500 index of 1.63% by 0.69%.

Hit Ratio Analysis for Retail Stocks Package

Looking at the above table, we can see that I Know First provides a high hit ratio for all signals and forecasting horizons for the period from April 2020 to June 2021. It should be noted that as the time horizon gets longer, I Know First hit ratios gradually increase from the 50% ratio interval for the short-term horizons to 76% at the Top 20 Signal subset for 1 year. All across the board, the hit ratios increase as the time horizon gets longer the hit ratio increases for the All Signal indicators by 8%, Top 20 by 26% Top 10 by 34%, and 5 Signals by 36%. Examining Table 2 shows that a high hit ratio is associated with a high average return, and as the forecast range expands, the return increases in performance.

Looking at Figure 5, it is clear that at the short term horizons the hit ratios are relatively low at all signal indicators but the hit ratios increase over the long term horizons showing the I Know First Algorithm is able to successfully predict most of the movements of the retail market better than the S&P 500 index. 

The COVID-19 pandemic is having a significant effect on the US and the global stock market, specifically the retail division, as many smaller retail business shops lost revenue and profit as a result of having less business due to the pandemic. Larger public retail companies such as Amazon, Apple, Microsoft, and Tesla all gained a 100 billion profit during the pandemic as consumers considered more deliveries, and found a growing need for technology.

Conclusion

This report looked at the live performance forecast of I Know First data for Retail Stocks from April 2020 to June 2021. From the above data, we can observe that the I Know First Algorithm is exceeding the S&P 500 benchmark index across all signal filtering subsets and forecasting periods. Data from Figures 3 and 4 above shows I Know First was able to generate returns, over 96% for top 5 retail stocks in one year, and we can see that I Know First Algorithm’s short-term horizon results have exceeded the S&P500 index. For the 14 day period, the Top 5 Signal index 3.88% exceeded the S&P500 index of 1.63% by 2.25%; the Top 10 Signal index of 3.05% by 1.42%; and the Top 20 Signal index of 2.32% by 0.69%. As a result, I predict that I Know First’s algorithm will be bullish in their predictions of prices of retail stocks in future years and we can be assured that I Know First will provide a successful long-term investment.