摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑-每日新闻-关于机器学习的最新研究结果已经发表。根据NewsRx编辑在布拉格的新闻报道，该研究指出：“我们利用机器学习技术研究了全球股票预期收益率在不同预测区间上的预测能力。我们发现，无论是在美国还是在国际上，收益率的可预测性都随着预测区间的延长而降低。”我们的新闻编辑从布拉格查尔斯大学的研究中获得了一句话：“尽管如此，我们提供了证据表明，即使考虑了交易成本，特别是当我们考虑更长的预测期限时，使用公司特有的特征仍然可以保持盈利。”我们强调了与频繁再平衡相关的较高交易成本和较短期限内较高回报之间的权衡。我在增加预测期限的同时，与再平衡期相匹配，增加了美国在交易成本后的风险调整回报。我们使用双重排序和减少营业额策略，即买入/持有利差，结合了对多个期限内预期回报的预测。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learn ing have been published. According to news reporting originating from Prague, Cz ech Republic, by NewsRx editors, the research stated, "We investigate the predic tability of global expected stock returns across various forecasting horizons us ing machine learning techniques. We find that the predictability of returns decr eases with longer forecasting horizons both in the U.S. and internationally." Our news editors obtained a quote from the research from the Charles University of Prague, "Despite this, we provide evidence that using firm -specific characte ristics can remain profitable even after accounting for transaction costs, espec ially when we consider longer forecasting horizons. Studying the profitability o f long -short portfolios, we highlight a trade-off between higher transaction co sts connected to frequent rebalancing and greater returns on shorter horizons. I ncreasing the forecasting horizon while matching the rebalancing period increase s risk -adjusted returns after transaction costs for the U.S. We combine predict ions of expected returns at multiple horizons using double -sorting and a turnov er reducing strategy, buy/hold spread."
NETL
NSTL