Source: DeepHub IMBA This article is about 6800 words, and it is recommended to read for 10+minutes This article will discuss the techniques to obtain tangible value from the dataset using hypothesis testing, feature engineering, and time series modeling methods. Using statistical tests and machine learning to analyze and predict the performance of solar power … Read more
XGBoost and LightGBM are currently very popular tree-based machine learning models, both demonstrating efficient performance. However, they have different characteristics in certain situations. Simple Comparison of XGBoost and LightGBM Training Speed LightGBM has a significant advantage over XGBoost in terms of training speed. This is because LightGBM uses some efficient algorithms and data structures, such … Read more
Author: Jason Brownlee Translation: wwl Proofreader: Wang Yutong This article contains about 3300 words, and is recommended to be read in 10minutes This article introduces how to use XGBoost for time series forecasting, including transforming time series into a supervised learning prediction problem, using forward validation for model evaluation, and providing actionable code examples. For … Read more
import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns import xgboost as xgb from sklearn.metrics import mean_squared_error color_pal = sns.color_palette() plt.style.use('fivethirtyeight') df = pd.read_csv('AAPL Hourly.csv') df = df[['timestamp', 'close']] df = df.set_index('timestamp') df.plot(style='.', figsize=(15, 5), color=color_pal[0], title='stock growth') plt.show() df.head() mean = df['close'].mean() mean 162.3033402402023 df.index = pd.to_datetime(df.index) … Read more
Source: DeepHub IMBA This article is about 3300 words, suggested reading time is 10 minutes. This article will introduce the BiTCN model, which utilizes two Temporal Convolutional Networks (TCN) to encode past and future covariates while maintaining computational efficiency. In the field of time series forecasting, model architecture often relies on Multi-Layer Perceptron (MLP) or … Read more
Using machine learning for investment has always been a popular subject. In recent years, deep learning models have attracted a lot of attention, especially in the field of computer vision. Therefore, the paper introduced here provides a brand new approach by using the currently hottest computer vision neural network: Convolutional Neural Network (CNN) to predict … Read more
Sea Temperature Forecast Model Based on PCA and LSTM Full text can be downloaded on PC at the following address: http://www.hyyb.org.cn/Magazine/Show.aspx?ID=3464 Reading Notes Authors: Li Jingshi1 2 Kuang Xiaodi1 2 Li Qiong3 He Enye1 2 Zhang Yubai3 Yuan Chengyi4 Zhang Yanlin5 Affiliations: 1. National Marine Environmental Forecasting Center, Beijing 100081; 2. Key Laboratory of Marine … Read more
Research on LSTM Water Level Prediction Model Based on Improved Attention Mechanism Ma Fei 1, Tu Zhenyu 1*, Zhu Songting 2, Xiang Xinyue 1, Sun Yifei 1, Fang Qiang 1 (1. School of Information Engineering, Nanchang Engineering College, Nanchang, Jiangxi, 330099; 2. Jiangxi Flood Control Information Center, Nanchang, Jiangxi, 330009) Abstract In order to further … Read more
♚ Author: Yishui Hancheng, CSDN Blog Expert, Research Directions: Machine Learning, Deep Learning, NLP, CV Blog: http://yishuihancheng.blog.csdn.net Traditional linear models struggle with multivariate or multi-input problems, whereas neural networks like LSTM excel at handling multiple variables, making them suitable for time series prediction tasks. In the following article, you will learn how to build an … Read more
Research on LSTM Model for River Dissolved Oxygen Prediction Optimized by Attention Mechanism Zhou Quan1, Hu Xuanming2, Wang Dongkun2, Zhang Wucai1, Chen Zhongying1, Wang Jinpeng1, Wang Pengyang2, Ren Xiuwen1 1. South China Institute of Environmental Sciences, Ministry of Ecology and Environment, Key Laboratory of Water Environment Simulation and Pollution Control, Guangzhou, Guangdong 5105302. University of … Read more