Feel free to write us
a message.
The use of machine learning in the quantitative investment field is expanding and the right usage is encouraging many to explore the world of investing. To generate market advantages and enable our users to enjoy the greatest stock selection process, we are choosing beneficial data, suitable to give us not only the Artificial-Intelligence-driven tool for making the right stock decisions but also interpretability and transparency of process and results. Our calculations include data collected for the last 30 years, allowing us to get more robust and reliable results.
As part of the research used, for example, in the StockPicker application we have been researching the selection of variables enterings. When there are too many variables, the model has a worse ability to generalize and therefore is less robust and more prone to errors.
- If you need to extract information from your data, do not hesitate to contact us.
It has been a year (03. 06. 2020 – 28. 05. 2021) already since we started trading with our “StockPicker” strategy on real Interactive Broker accounts. Therefore, we bring more detailed results, including graphs and comparisons with a benchmark, in our case the S&P 500 Index.
(more…)
Undervalued and overvalued stocks in our model are currently calculated as part of a proof of concept solution that is based on proprietary software with inner limitations.
Therefore, a new robust production system is being prepared. In this way, we can take advantage of synergies with existing components from other areas, for example for postprocessing of results. (more…)
Take a look at the first report of our results in 2021.
In January, our system, based on a portfolio of 20 relatively most undervalued* stocks from the S&P 100 index in the Long position and 20 relatively most overvalued* stocks in the Short position, achieved a 4.1 % yield. The S&P 500 index fell by 1.1 % over the same period.
The performance of the system is 39.52 % at an annual recalculation. Detailed results can be viewed here.
You can view a report with for the month of February in our StockPickingLab application, or in the application of the partner company StockPicker.eu.
Factors that influence the decision-making of the model (now for the February stock selection, the calculation took place on 31 January 2021).
Variable | Coeff | Weight |
|---|---|---|
| Constant | 0,01% | 0,03% |
| Autocorrelation 5 | 1,79% | 6,46% |
| Momentum 252 - 22 | 3,43% | 12,40% |
| USD Volume Relative Change 22 vs 44 | -1,48% | 5,35% |
| CCI 4 | -2,74% | 9,91% |
| SUV Resid 252 | 0,76% | 2,73% |
| SUV Coef 126 | -1,38% | 4,99% |
| SUV Coef 104 Weeks | -1,32% | 4,78% |
| AR LogPrice 52 Weeks | 2,49% | 9,00% |
| DividendPerShare DPS | -2,22% | 8,01% |
| EarningsPerShare EPS | 0,22% | 0,79% |
| MarketCapitalization MV | -2,83% | 10,20% |
| OperatingCashFlow OperatingCF | 0,50% | 1,81% |
| SalesPerShare SPS | -0,14% | 0,52% |
| PriceBookValueRatio PTBV Change 126 Days | -0,46% | 1,65% |
| PriceCashFlowRatio PCF Change 126 Days | -1,27% | 4,60% |
| PriceEarningsRatio PE Position 66 Days | -1,05% | 3,78% |
| PriceBookValueRatio PTBV Position 252 Days | -3,60% | 13,01% |
The Momentum Formula II system did not trade in January due to a persistent error by Interative Brokers in placing stoplosses.
*Calculation of over/ undervaluation is based on the analysis of macroperdictors and company-specific predictors, see above.
We are launching the StockPickingLab section, through which you gain access to the relatively most undervalued and overvalued stocks within the S&P 100 index.
- You can view the results of the Stock Picker system in real operation here. The average annual yield is 17,69 %, while the maximum drawdown is -13,72 %.
- Factors that influence the decision-making of the model are listed in the previous article.
- Detailed information and access to the system are under this article.
We provide an analytical report as the output of the developed software for analysts in the capital markets. This is by no means an investment recommendation. We do not provide any financial services. Our activity is the development of software based on AI methods. We are developing the model in cooperation with Mendel University in Brno and the University of Economics in Prague. For more information or cooperation with our company, do not hesitate to contact us.
