513 讨论班 –金融时间序列分类模型及与目前提取数据规律方法

（朱浩 杨家耀）

题目：金融时间序列分类综述、数据包含的规律类型以及提取规律方法

主讲人：朱浩 杨家耀

时间：2020年12月13日下午2:00--3:00

地点：大理大学古城校区，工程学院 409

简介：1）金融时间序列分类综述。

         遇到的问题，采取的方法，以及得到的结果综述和比较。

          2）数据包含的规律类型。

         动量规律，组合特征以及包含隐含变量的数据规律构造。

         提取这些规律的方法：不同模型提取规律的结果对比，包括传统机器学习算法，统计算法，深度学习算法。

参考资料：1.  Susto, Antonio G . Time-Series Classification Methods: Review and Applications to Power Systems Data[J]. Big Data Application in Power Systems, 2018:179-220.                                  

                 2.Deniz Ersan1 Chifumi Nishioka2 Ansgar Scherp3.Comparison of machine learning methods for fnancial time series forecasting at the examples of over 10 years of daily and hourly data of DAX 30 and S&P 500 Received: 17 June 2019 / Accepted: 24 October 2019  Springer Nature Singapore Pte Ltd. 2019

                  3.Hatami N , Gavet Y , Debayle J . Bag of recurrence patterns representation for time-series classification[J]. Pattern Analysis and Applications, 2019, 22(3):877-887.

                  4.Caporin M , Storti G . Financial Time Series: Methods and Models[J]. Journal of Risk and Financial Management, 2020, 13.

                   5.Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Deep learning for time series classification: a review[J]. DATA MINING AND KNOWLEDGE DISCOVERY, 2019.

                   6.Electric Power Research Institute, China Southern Power Grid, Guangzhou, CDynamic Multi-scale Convolutional Neural Network for Time Series Classifification Digital Object Identififier 10.1109/ACCESS.2017.DOI

                   7.Fons E , Dawson P , Zeng X J , et al. Evaluating data augmentation for financial time series classification[J]. Papers, 2020.

                    8.Wang W , Liu H , Yu L , et al. Extreme learning machine for time sequence classification[J]. Neurocomputing, 2016, 174.

                    9.Assis C A S , Machado E J , Pereira A C M , et al. Hybrid deep learning approach for financial time series classification[J]. Revista Brasileira De Computação Aplicada, 2018, 10(2):54-63.

                    10.Du B , Fernandez-Reyes D , Barucca P . Image Processing Tools for Financial Time Series Classification[J]. Papers, 2020.

                     11.Karim F , Majumdar S , Darabi H . Insights into LSTM Fully Convolutional Networks for Time Series Classification[J]. IEEE Access, 2019, 7:67718-67725.

                    12.Karim F , Majumdar S , Darabi H , et al. LSTM Fully Convolutional Networks for Time Series Classification[J]. IEEE Access, 2018, 6(99):1662-1669.

                    13.Mohammed S A , Abu Bakar M A , Ariff N M . Volatility forecasting of financial time series using wavelet based exponential generalized autoregressive conditional heteroscedasticity model[J]. Communications in Statistics: Theory and Methods, 2020.

                    14.Liu Guang · Wang Xiaojie · Li Ruifan Multi-Scale RCNN Model for Financial Time-series Classifification Received: date / Accepted: date

                    15.Zhiguang Wang, Weizhong Yan GE Global Research {zhiguang.wang, yan}@ge.com Time Series Classifification from Scratch with Deep Neural Networks: A Strong Baselin