神经网络股票排序预测器中的异常收益

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

摘要翻译：
使用人工神经网络(ANN)，从价值线指数中确定大约1500只股票，根据它们在下一个季度的预测价格变化进行排序。对网络的输入仅包括每种股票（按季度，不累加）的价格和收益的前十个季度百分比变化，转换成一个约为零的相对等级。分别从10、20、…、100个排名靠前的股票（多头投资组合）、10、20、…、100个排名靠后的股票（空头投资组合）及其对冲集合（多空投资组合）中构造30个模拟投资组合。在从1994年第三季度末到2001年第四季度的29个季度的模拟中，复制了2002年使用的相同方法的真实世界交易，所有投资组合都固定持有一个季度。结果与标准普尔500，价值线宇宙本身，使用专有的“价值线排序系统”（该方法在某些方面类似）交易股票宇宙，以及对相同股票进行排序的鞅方法进行了比较。网络预测器产生的累积回报显著超过标准普尔500、整体宇宙、鞅和价值线预测方法产生的回报，并且不受交易成本的侵蚀。人工神经网络显示显著正的Jensen's alpha,即异常的风险调整预期收益。其全球性能的时间序列显示出明显的反持久性。然而，它的性能明显优于简单的一步鞅预测器、价值线系统本身以及简单的买入和持有策略，即使考虑了交易成本。
---
英文标题：
《Anomalous Returns in a Neural Network Equity-Ranking Predictor》
---
作者：
J.B. Satinover (Univ. Nice) and D. Sornette (ETH Zurich)
---
最新提交年份：
2008
---
分类信息：

一级分类：Quantitative Finance        数量金融学
二级分类：General Finance        一般财务
分类描述：Development of general quantitative methodologies with applications in finance
通用定量方法的发展及其在金融中的应用
--
一级分类：Physics        物理学
二级分类：Adaptation and Self-Organizing Systems        自适应和自组织系统
分类描述：Adaptation, self-organizing systems, statistical physics, fluctuating systems, stochastic processes, interacting particle systems, machine learning
自适应，自组织系统，统计物理，波动系统，随机过程，相互作用粒子系统，机器学习
--
一级分类：Physics        物理学
二级分类：Physics and Society        物理学与社会
分类描述：Structure, dynamics and collective behavior of societies and groups (human or otherwise). Quantitative analysis of social networks and other complex networks. Physics and engineering of infrastructure and systems of broad societal impact (e.g., energy grids, transportation networks).
社会和团体（人类或其他）的结构、动态和集体行为。社会网络和其他复杂网络的定量分析。具有广泛社会影响的基础设施和系统（如能源网、运输网络）的物理和工程。
--

---
英文摘要：
  Using an artificial neural network (ANN), a fixed universe of approximately 1500 equities from the Value Line index are rank-ordered by their predicted price changes over the next quarter. Inputs to the network consist only of the ten prior quarterly percentage changes in price and in earnings for each equity (by quarter, not accumulated), converted to a relative rank scaled around zero. Thirty simulated portfolios are constructed respectively of the 10, 20,..., and 100 top ranking equities (long portfolios), the 10, 20,..., 100 bottom ranking equities (short portfolios) and their hedged sets (long-short portfolios). In a 29-quarter simulation from the end of the third quarter of 1994 through the fourth quarter of 2001 that duplicates real-world trading of the same method employed during 2002, all portfolios are held fixed for one quarter. Results are compared to the S&P 500, the Value Line universe itself, trading the universe of equities using the proprietary ``Value Line Ranking System'' (to which this method is in some ways similar), and to a Martingale method of ranking the same equities. The cumulative returns generated by the network predictor significantly exceed those generated by the S&P 500, the overall universe, the Martingale and Value Line prediction methods and are not eroded by trading costs. The ANN shows significantly positive Jensen's alpha, i.e., anomalous risk-adjusted expected return. A time series of its global performance shows a clear antipersistence. However, its performance is significantly better than a simple one-step Martingale predictor, than the Value Line system itself and than a simple buy and hold strategy, even when transaction costs are accounted for.
---
PDF链接：
https://arxiv.org/pdf/0806.2606

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：神经网络 神经网 Quantitative respectively Applications 产生 进行 变化 季度 预测