Note: Overlapping labels 重叠的标签, AI for Trading
问题重叠标签(overlapping labels)问题是使用金融数据训练预测模型遇到的一个问题。如下图所示，假设我们要训练一个模型预测未来一周的收益，最简单的情况下我们会用某一天T的后一周连续收益作为训练的标签(label, i.e. 那个y)。这样每天的样本例子都有一个未来一周的label对应。但由于金融数据有自相关性，连续几天的label通常是相互关联的——这就和大多数机器学习模型的假设冲突
笔记 - Tree-based models with financial data, AI for Trading
Importance of Random Column Selection / 随机列选择的重要性Sometimes one feature will dominate in finance. If you don’t apply some type of random feature selection, then your trees will not be that different (i
Validation for Financial Data 金融数据的验证集
Furthermore, when working with financial data, we can bring practitioners' knowledge of markets and financial data to bear on our validation procedures. We know that since markets are competitive, fac
Cross Validation for Time Series 时间序列数据的交叉验证
Methods for choosing training, testing and validation sets for time-series data work a little differently than the methods described so far. The main reasons we cannot use the previously described met
期权高频交易系统 简单揭秘
温故而知新。框架上图是我眼中的最简交易系统，它分为几个部分：网关(Gateway): 负责和交易所/经纪人（远端）打交道。一方面接收行情数据(报价更新，订单更新等），另一方面把交易指令传给远端.定价引擎(Pricing Engine): 接入的行情数据需要转换成策略需要的报价。对于衍生品来说，它的输出应当至少包含衍生品的理论价格。定价引擎可能还有额外的输入，比如对于期权定价而言，，一般会使用类Bl