时间序列专题学习

[[时间序列预测]]

• 时间序列分析的核心是挖掘该时间序列的自相关性

• [[石川@写给你的金融时间序列分析]]

• DONE [[随风@时间序列分析]] 知乎上写的很好教程：包括基础知识讲解(还是石川讲得更加详细)以及通过支付宝数据演示如何利用各种方法和模型。

  • [[时间序列预测/基本数学概念]]

  • [[TCN]]

• DONE [[字节@漫谈时间序列预测]]
  completed:: [[2023/02/27]]

• [[Time Series Forecasting With Deep Learning: A Survey]] 牛津大学关于时间序列预测深度学习方法总结

• [[Deep learning for time series classification: a review]] 时间序列分类

[[时间序列分解]]

• 时间序列分解1 - 知乎 (zhihu.com)

比赛相关

• [[Web Traffic Time Series Forecasting]]

  • [[Web Traffic Time Series Forecasting 1st place solution]]

  • 回顾kaggle Web Traffic Time Series Forecasting及对时序比赛讨论 - 知乎 (zhihu.com)

• 百度KDD Cup2022-Top方案总结 - 知乎 (zhihu.com)

• Kaggle 时间序列预测挑战的获胜解决方案 - 知乎 (zhihu.com)

• [[M5 Accuracy Competition]]

  • gbdt不适用于什么样的时间序列问题 - 知乎 (zhihu.com) #[[gbdt 时间序列]]

    • [[@The M5 Accuracy competition: Results, findings and conclusions]]

    • [[@Forecasting with trees]]

    • Forcasting with trees(待续) - 知乎 (zhihu.com)

[[@Time-series Extreme Event Forecasting with Neural Networks at Uber]]

[[Time Series Transformer]]

• TODO [[@From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba]]

• TODO [[@Gated Transformer Networks for Multivariate Time Series Classification]]

• TODO [[@Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting]]

• TODO [[@Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting]]

• TODO [[@FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting]]

• [[@Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting]]

• [[ConvTrans]] 【时间序列】Transformer for TimeSeries时序预测算法详解 - 知乎 (zhihu.com)

[[@A Transformer-based Framework for Multivariate Time Series Representation Learning]]

• A Transformer-based Framework for Multivariate Time Series Representation Learning - 知乎 (zhihu.com)

[[N-BEATS]]

[[DeepAR]] 用概率预测代替点估计，通过采用求平均方式得到最终预测

• https://zhuanlan.zhihu.com/p/201030350

• https://zhuanlan.zhihu.com/p/377342633

[[@Do We Really Need Deep Learning Models for Time Series Forecasting?]]

[[Recurrent Neural Networks for Multivariate Time Series with Missing Value]]

• 时间序列缺失值问题

• 时间序列的不等间隔问题

• rnn变体系列之——GRU-D - 知乎 (zhihu.com)

时间序列增强

• Time Series Data Augmentation for Deep Learning: A Survey