
Ð’ наÑтоÑщей работе иÑÑледуетÑÑ Ð¿Ñ€Ð¸Ð¼ÐµÐ½ÐµÐ½Ð¸Ðµ методов машинного Ð¾Ð±ÑƒÑ‡ÐµÐ½Ð¸Ñ Ð´Ð»Ñ Ð¿Ñ€Ð¾Ð³Ð½Ð¾Ð·Ð¸Ñ€Ð¾Ð²Ð°Ð½Ð¸Ñ Ð²Ñ€ÐµÐ¼ÐµÐ½Ð½Ñ‹Ñ… Ñ€Ñдов. РаÑÑмотрены варианты иÑÐ¿Ð¾Ð»ÑŒÐ·Ð¾Ð²Ð°Ð½Ð¸Ñ ARIMA моделей, нейроÑетей и алгоритма градиентного буÑтинга. Ð’ качеÑтве обучающих выборок иÑпользовалиÑÑŒ цены на акции, а также данные, полученные в результате Ð¿Ñ€Ð¸Ð¼ÐµÐ½ÐµÐ½Ð¸Ñ Ñ‚ÐµÑ…Ð½Ð¸Ñ‡ÐµÑких индикаторов. Ðа оÑнове Ñтих методов и обучающих выборок были Ñделаны прогнозы дальнейшего ценообразованиÑ, поÑтроены графики и поÑчитаны метрики Ð´Ð»Ñ ÐºÐ°Ð¶Ð´Ð¾Ð³Ð¾ из иÑÑледуемых методов. Были получены теоретичеÑкие и практичеÑкие результаты, проведён анализ и Ñделаны выводы об ÑффективноÑти иÑпользованных алгоритмов.
This paper explores the application of machine learning methods for time series forecasting. The options for using ARIMA models, neural networks and the gradient boosting algorithm are considered. As training samples, stock prices were used, as well as data obtained as a result of applying technical indicators. Based on these methods and training samples, further pricing forecasts were made, graphs were built and metrics were calculated for each of the studied methods. Theoretical and practical results were obtained, analysis was carried out, and conclusions were drawn about the effectiveness of the algorithms used.
нейÑоÑеÑи, machine learning, маÑинное обÑÑение, ÑондовÑй ÑÑнок, ARIMA, LSTM, neural networks, programming, stock market, пÑогÑаммиÑование, XGBoost
нейÑоÑеÑи, machine learning, маÑинное обÑÑение, ÑондовÑй ÑÑнок, ARIMA, LSTM, neural networks, programming, stock market, пÑогÑаммиÑование, XGBoost
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
