We investigate the benefits of feature selection, nonlinear modelling and online learning when forecasting in financial time series. We consider the sequential and continual learning sub-genres of online learning. The experiments we conduct show that there is a benefit to online transfer learning, beyond the sequential updating of recursive least-squares models. We show that feature representation transfer via radial basis function networks, which make use of clustering algorithms to construct a kernel Gram matrix, are more beneficial than treating each training vector as separate basis functions, as occurs with kernel Ridge regression. We also demonstrate quantitative procedures to determine the very structure of the networks. Finally, we conduct experiments on the log returns of financial time series and show that these online transfer learning models are able to outperform a random walk baseline, whereas the offline learning models struggle to do so.

翻译：我们在财务时间序列中进行预测时,调查地物选择、非线性建模和在线学习的好处。我们考虑在线学习的顺序和持续学习子类型。我们进行的实验表明,除了连续更新递增的最小方形模型之外,网上转移学习也有益处。我们显示,通过辐射基功能网络进行地物代表转换,利用群集算法来构建核心格拉姆矩阵,比将每个培训矢量作为单独的基础功能对待更为有益,就像内核脊脊回归那样。我们还展示了确定网络结构的量化程序。最后,我们进行了财务时间序列日志回报实验,并表明这些在线转移学习模型能够超越随机行走基线,而离线学习模型则努力这样做。