https://github.com/avijay24/predictingonlinenewspopularity
Using Machine Learning Algorithms, created a model for predicting the popularity of an online news article on Mashable with 79% accuracy along with forecasting a profitability of $1,182,400 using the cost matrix for model
https://github.com/avijay24/predictingonlinenewspopularity
cost-matrix data-science-projects machine-learning mashable news-popularity-prediction predictive-analytics python
Last synced: 5 days ago
JSON representation
Using Machine Learning Algorithms, created a model for predicting the popularity of an online news article on Mashable with 79% accuracy along with forecasting a profitability of $1,182,400 using the cost matrix for model
- Host: GitHub
- URL: https://github.com/avijay24/predictingonlinenewspopularity
- Owner: avijay24
- Created: 2023-08-14T22:03:17.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-10-23T18:22:38.000Z (over 2 years ago)
- Last Synced: 2025-02-24T12:22:13.180Z (over 1 year ago)
- Topics: cost-matrix, data-science-projects, machine-learning, mashable, news-popularity-prediction, predictive-analytics, python
- Language: Jupyter Notebook
- Homepage:
- Size: 15 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# PredictingOnlineNewsPopularity
Using Machine Learning Algorithms, created a model for predicting the popularity of an online news article on Mashable with 79% accuracy along with forecasting a profitability of $1,182,400 using the cost matrix for model.
Problem Statement:
The dataset is about articles published by Mashable in a period of two years.
The Mashable team wants to identify articles which will become popular based on the historical data.
The team wants to identify and set the right price for advertisements based on their popularity.
Project Goal:
The goal is to predict if the article is among the most popular ones based on sharing in social networks.
We decided to find the best predictive model in the dataset by data engineering and utilizing Machine Learning algorithms to achieve the goal.