STOCK PRICE MOVEMENTS PREDICTION CONSIDERING SOCIAL MEDIA SENTIMENT
Stock price movements are complex and difficult to predict, primarily due to the high volatility of the stock market itself. This research aims to compare the performance of models in predicting Tesla’s stock price movements using the Random Forest and Naive Bayes models, considering sentiment pr...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/83273 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| id |
id-itb.:83273 |
|---|---|
| spelling |
id-itb.:832732024-08-06T14:29:39ZSTOCK PRICE MOVEMENTS PREDICTION CONSIDERING SOCIAL MEDIA SENTIMENT Pramudia Santosa, Nanda Indonesia Final Project Stock price movements, Sentiment, BERT, Random Forest INSTITUT TEKNOLOGI BANDUNG https://digilib.itb.ac.id/gdl/view/83273 Stock price movements are complex and difficult to predict, primarily due to the high volatility of the stock market itself. This research aims to compare the performance of models in predicting Tesla’s stock price movements using the Random Forest and Naive Bayes models, considering sentiment predictors obtained using BERT and LSTM models. The data used includes historical prices, moving averages, sentiment, and retweets from tweets related to Tesla from January 1, 2024, to May 31, 2024. By using predictors in the form of historical Tesla stock price data and technical analysis, augmented with tweet data including sentiment and retweet counts, both the Random Forest and Naive Bayes models show a significant increase in accuracy, ranging from 22.6% to 30%. text |
| institution |
Institut Teknologi Bandung |
| building |
Institut Teknologi Bandung Library |
| continent |
Asia |
| country |
Indonesia Indonesia |
| content_provider |
Institut Teknologi Bandung |
| collection |
Digital ITB |
| language |
Indonesia |
| description |
Stock price movements are complex and difficult to predict, primarily due to the high
volatility of the stock market itself. This research aims to compare the performance
of models in predicting Tesla’s stock price movements using the Random Forest and
Naive Bayes models, considering sentiment predictors obtained using BERT and LSTM
models. The data used includes historical prices, moving averages, sentiment, and
retweets from tweets related to Tesla from January 1, 2024, to May 31, 2024. By
using predictors in the form of historical Tesla stock price data and technical analysis,
augmented with tweet data including sentiment and retweet counts, both the Random
Forest and Naive Bayes models show a significant increase in accuracy, ranging from
22.6% to 30%. |
| format |
Final Project |
| author |
Pramudia Santosa, Nanda |
| spellingShingle |
Pramudia Santosa, Nanda STOCK PRICE MOVEMENTS PREDICTION CONSIDERING SOCIAL MEDIA SENTIMENT |
| author_facet |
Pramudia Santosa, Nanda |
| author_sort |
Pramudia Santosa, Nanda |
| title |
STOCK PRICE MOVEMENTS PREDICTION CONSIDERING SOCIAL MEDIA SENTIMENT |
| title_short |
STOCK PRICE MOVEMENTS PREDICTION CONSIDERING SOCIAL MEDIA SENTIMENT |
| title_full |
STOCK PRICE MOVEMENTS PREDICTION CONSIDERING SOCIAL MEDIA SENTIMENT |
| title_fullStr |
STOCK PRICE MOVEMENTS PREDICTION CONSIDERING SOCIAL MEDIA SENTIMENT |
| title_full_unstemmed |
STOCK PRICE MOVEMENTS PREDICTION CONSIDERING SOCIAL MEDIA SENTIMENT |
| title_sort |
stock price movements prediction considering social media sentiment |
| url |
https://digilib.itb.ac.id/gdl/view/83273 |
| _version_ |
1822998053621071872 |