https://github.com/harmanveer-2546/ad-click-prediction-analysis-and-insights

To predict whether a user will click on ad or not.
https://github.com/harmanveer-2546/ad-click-prediction-analysis-and-insights

ads analysis classification-report click insights linearregression matplotlib numpy onehotencoder pandas pipeline prediction preprocessing randomforestclassifier seaborn sklearn sklearn-compose sklearn-library sklearn-metrics standardscaler

Last synced: 15 days ago
JSON representation

To predict whether a user will click on ad or not.

• Host: GitHub
• URL: https://github.com/harmanveer-2546/ad-click-prediction-analysis-and-insights
• Owner: harmanveer-2546
• Created: 2024-09-11T17:33:07.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2024-09-17T17:17:05.000Z (about 2 months ago)
• Last Synced: 2024-10-31T13:04:25.395Z (15 days ago)
• Topics: ads, analysis, classification-report, click, insights, linearregression, matplotlib, numpy, onehotencoder, pandas, pipeline, prediction, preprocessing, randomforestclassifier, seaborn, sklearn, sklearn-compose, sklearn-library, sklearn-metrics, standardscaler
• Language: Jupyter Notebook
• Homepage:
• Size: 4.24 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Ad Click Prediction

At its most basic, targeted advertising can mean that ads are chosen for their relevance to site content, assuming that they will then be relevant to the

site audience as well. Online advertisers can use different methods to target a particular advertisement to the user based on their traits. Most companies do this as part 

of social media like Facebook, LinkedIn, etc. But most of the time the process goes wrong and the advertisement does not reach its target audience because it is sent out 

without actually understanding the probability of the occurring click. The goal is to predict if a user would click on an advertisement based on the features of the user. 

### Dataset-

The dataset analyzed contains the following columns: id, full_name, age, gender, device_type, ad_position, browsing_history, time_of_day, and click. The primary objective was 

to understand user behavior around ad clicks by examining patterns in age, gender, device usage, browsing history, and other factors, along with building predictive models using 

machine learning.

### Conclusion-

This analysis highlights the importance of understanding user demographics, behavior patterns, and the timing of interactions in order to optimize ad placements. Gender, age, 

and device type all play significant roles in determining whether users are likely to click on an ad. While our initial predictive models show promise, deeper analysis and more 

advanced models could provide more robust results.

Overall, these insights can help advertisers and marketers better tailor their ad campaigns and improve targeting strategies to maximize engagement.