Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций
Конференция: Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-III 2024); Krasnoyarsk; Krasnoyarsk
Год издания: 2025
Идентификатор DOI: 10.1051/itmconf/20257201002
Аннотация: The paper presents selecting stocks for an investment portfolio algorithm, alternative to standard mathematical programming optimal portfolio methods. To implement the algorithm, a modification of the Random Forest machine learning model is proposed. At the first step, the algorithm builds a decision tree based on forecasts using tПоказать полностьюhe naive method and the ARIMA method, and then it forms a “forest” of trees from random subsamples. The algorithm was tested on different time intervals on the instruments of two exchange indices. Its implementation showed good results - at least 78% of the selected stocks increased in price over the forecast period.
Журнал: ITM Web of Conferences
Номера страниц: 1002
Место издания: Krasnoyarsk