liuyanjun-001

HARNet

TensorFlow implementation of the HARNet model for realized volatility forecasting.

HetroPanelAR

Replication package for estimation of moments of heterogeneous autoregressions (https://arxiv.org/abs/2306.05299)

ml-visuals

🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

reinforcement-learning-an-introduction-chinese

《Reinforcement Learning: An Introduction》（第二版）中文翻译

timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

transformer-time-series-prediction

proof of concept for a transformer-based time series prediction model

LSTM_GARCH

A Python implementation of a Hybrid LSTM-GARCH model for volatility forecasting

CV-Surveys

计算机视觉相关综述。包括目标检测、跟踪........

Sentiment-Analysis-and-Stock-Values

Sentiment analysis of economic news headlines and examining their effects on stock market changes without the full article or analysis. Awareness and click generation are important roles for business news headlines as well. The effect can be demonstrated.

Undergraduate-Thesis

基于LDA主题模型的投资者情绪对股价影响研究

neuralforecast

Scalable and user friendly neural :brain: forecasting algorithms.

bitcoin_volatility_forecasting

GARCH and Multivariate LSTM forecasting models for Bitcoin realized volatility with potential applications in crypto options trading, hedging, portfolio management, and risk management

TSFpaper

This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the type of model.

StackedAE_BayesianOptimization_TCN

GA-TCN-LSTM

An Ensemble DL Model Tuned with Genetic Algorithm for Oil Production Forecasting.

forecasting

Time-series forecasting with Deep Learning: RNN, LSTM, GRU, Rolling RNN/LSTM/GRU

Sentiment-Analysis-Chinese-pytorch

中文的情感分析任务：基于Bi-LSTM+Attention模型，对2万条中文影评数据进行情感分类。Chinese sentiment analysis task: Based on the Bi-LSTM+Attention model, sentiment classification is performed on 20,000 Chinese film review data.

Python_DataAnalysis

Python 数据分析案例。包含【电影评论分析】、【慕课数据分析】、【医疗花销分析】、【心脏病、癌症、糖尿病预测】

python-DataAnalysis

基于python与Anaconda Navigator软件的历年影片数据分析，通过数据再基于机器学习来获取影片的最佳阵容，最后预测以最佳整容去拍摄一部电影时所获取的票房与评分。

TOP250_douban_movies

TOP250豆瓣电影短评爬虫+数据分析

Chinese-movie-comments-sentiment-analysis-pytorch

中文电影评论情感分类，pytorch实现Text-CNN。

douban_sentiment_analysis

基于朴素贝叶斯实现的豆瓣影评情感分析

TOP250movie_douban

TOP250豆瓣电影短评：Scrapy 爬虫+数据清理/分析+构建中文文本情感分析模型

ConvMF

卷积神经网络（CNN）提取影评特征构建电影推荐系统，pytorch实现

AntSpider

1000万豆瓣电影/评论/名人/评分数据采集源码分享（内含千万电影数据集，可下载）

Classification-of-Movie-Reviews-with-Latent-Semantic-Analysis-Using-SVD

Natural Language Processing(NLP) is a broad set of techniques to derive meaning from words in a dataset. In this paper, we will cover one of the NLP techniques, the Latent Semantic Analysis technique. This is a part of unsupervised learning techniques in which models are not supervised using the training datasets, but instead, find the hidden patterns and insights from the given data. The main benefit of this technique is that the process can reduce the dimensionality of the original text-based data set which will be the movie review data set obtained from Kaggle in this project.

sentiment-classification

Neural sentiment classification of text using the Stanford Sentiment Treebank (SST-2) movie reviews dataset, logistic regression, naive bayes, continuous bag of words, and multiple CNN variants.

MovieReviewSentimentAnalysis

Sentiment Analysis and Emotion Classification of Movie Reviews from IMDb

BTC-LSTM-Predictor-

Due to the volatility of cryptocurrency speculation, investors will often try to incorporate sentiment from social media and news articles to help guide their trading strategies. One such indicator is the Crypto Fear and Greed Index (FNG) which attempts to use a variety of data sources to produce a daily FNG value for cryptocurrency. You have been asked to help build and evaluate deep learning models using both the FNG values and simple closing prices to determine if the FNG indicator provides a better signal for cryptocurrencies than the normal closing price data.

DeepLearning_BTC

Due to the volatility of cryptocurrency speculation, this project is looking to help build and evaluate deep learning models using the Crypto Fear and Greed Index values and closing prices to determine if the indicator provides a better signal for cryptocurrencies. By using the deep learning recurrent neural network to model bitcoin prices, one model will predict the closing price while the second model will use a window of closing prices to predict the nth closing price.