Top Quantitative Self-Media in the Industry Author: Smith Translated by: Fang’s Mantou 1 Introduction Using machine learning to predict the next period’s price or direction based on stock prices is not new, and it does not yield any meaningful predictions. In this article, we will break down the time series data of a series of … Read more
XGBoost is an effective implementation for gradient classification and regression problems.It is fast and efficient, performing excellently in various predictive modeling tasks and is widely favored among winners of data science competitions (e.g., Kaggle winners), even if it is not the best.XGBoost can also be used for time series forecasting, although it requires converting the … Read more
Author: Eryk Lewinson Translator: Wang Anxu Proofreader: zrx This article is approximately 4400 words long and is recommended for a 5-minute read. This article explores three methods of creating meaningful features using time-related information. Tags: Time Frame, Machine Learning, Python, Technical Demonstration Imagine you are starting a new data science project. The goal is to … Read more
PyTorch-Forecasting[1] makes time series forecasting using neural networks simple for data scientists and researchers. Why Accurate Forecasting is So Important? Forecasting time series is crucial in many scenarios and is highly relevant to machine learning practitioners. Take demand forecasting as an example, many use cases stem from this. Almost every manufacturer benefits from a better … Read more
This article uses a visual presentation to help you deeply understand the structure of the LSTM model. Recently, I have been learning about the application of LSTM in time series prediction, but I encountered a significant problem: after adding time steps to the traditional BP network, its structure becomes difficult to understand.At the same time, … Read more
Source: Deep Learning Enthusiasts This article is about 3300 words, and it is recommended to read for more than 10 minutes. This article uses a visual presentation to help you deeply understand the structure of LSTM models. I have recently been learning about the application of LSTM in time series prediction, but I encountered a … Read more
Do Time Series Forecasts Really Need Deep Learning Models? IntroductionTime series forecasting is a common task in machine learning with very wide applications, such as predicting energy consumption, traffic flow, and air quality. Traditional time series forecasting models often rely on rolling averages, vector autoregression, and autoregressive integrated moving averages. On the other hand, recent … Read more
Traditional linear models struggle to solve multivariable or multi-input problems, while neural networks like LSTM excel at handling multiple variables. This characteristic makes them useful for addressing time series prediction issues. In the following article, you will learn how to build an LSTM model using the deep learning library Keras to tackle multivariable time series … Read more
Research on land subsidence intelligent prediction method based on LSTM and Transformer——A case study of Shanghai PENG Wenxiang1,2,3,4,5，ZHANG Deying1,2,3,4,5 1. Shanghai Institute of Geological Survey, Shanghai 200072; 2. Shanghai Institute of Geological Exploration Technology, Shanghai 200072; 3. Key Laboratory of Land Subsidence Monitoring and Prevention, Ministry of Natural Resources of China, Shanghai 200072; 4. Shanghai … Read more
©Author | Light School | University of Chinese Academy of Sciences Research Direction | Machine Learning Zhihu Link: https://zhuanlan.zhihu.com/p/471014006 Editor| paperweekly Time series is one of my favorite research topics. Here I list the most commonly used methods for time series, including both theory and practice. The theoretical part mainly consists of high-quality interpretations created … Read more