It is important to have a rich and comprehensive data set for every system decision, including machine learning models. Only then can one build a robust and powerful model with desired performance. Otherwise, the developer would face the so-called GIGO (garbage in – garbage out) effect. It is an expression that says poor-quality input data provides poor-quality outputs. Although there are several data platforms automating the whole ETL (extract, transform, load) process, sometimes these solutions are overabundant, or the pre-made solutions might not meet your specific needs. (more…)

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.

(more…)