摘要
由机器人与机器学习每日新闻的新闻记者兼新闻编辑-研究人员详细介绍了人工智能的新数据。根据NewsRx记者在巴西圣保罗的新闻报道，研究表明，“由于价格变化与白噪音相似，预测金融市场的回报并不具有挑战性。”这项研究的资助者包括capes/print-brazil；纽约大学无线。我们的新闻记者从Universidade Pre Sbiteriana Mackenzie的研究中获得了一句话：“在本文中，我们提出了解决这一难题的新方法。利用全年一分钟零度的高频巴西股市数据，我们应用了各种统计和机器学习算法，包括ARIMA、双向长短期记忆(BiLSTM)和Attention、Transformers、n-beats、n-h我们的研究结果表明，基于回归和机器学习的预测方法的组合产生了最高的每笔交易利润。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in artific ial intelligence. According to news reporting from Sao Paulo, Brazil, by NewsRx journalists, research stated, “Forecasting returns in financial markets is notor iously challenging due to the resemblance of price changes to white noise.” Funders for this research include Capes/print-brazil; Nyu Wireless. Our news correspondents obtained a quote from the research from Universidade Pre sbiteriana Mackenzie: “In this paper, we propose novel methods to address this c hallenge. Employing high-frequency Brazilian stock market data at one-minute gra nularity over a full year, we apply various statistical and machine learning alg orithms, including ARIMA, Bidirectional Long Short-Term Memory (BiLSTM) with att ention, Transformers, N-BEATS, N-HiTS, Convolutional Neural Networks (CNNs), and Temporal Convolutional Networks (TCNs) to predict changes in the price ratio of closely related stock pairs. Our findings indicate that a combination of revers ion and machine learning-based forecasting methods yields the highest profit-per -trade.”
NETL
NSTL