Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 6

E-commerce Recommendation Engine

Presented By:-
Lahari Prathyusha
Sai Teja Chebrolu
Mayank Dashore
Veera Sakumalla
Pratish Kulkarni
Mohana Mona
Sahil Bhure
Sanika Pakade
Lalitha Dabi Varshini
Project Overview
Brief description of the project, its objectives, and its importance.
1) Underlining Concept
2) Item User Connection
3) AI/ML
4)Data Visualization
5)Learnings
Machine Learning
1.Project Overview: Recommendation Engine for Media and Entertainment Platform.
1.Objective: Enhance user engagement by recommending the content that user would like to
watch.
2.Approach: Collaborative filtering with demographic-based similarity.
3.Technical Details:
•Model: collaborative filtering,similarity metric,weighted average.
•Data: one-hot encoding, standardization, pivot table, feature alignment and Rating data split
into 80% training and 20% testing sets.
•Training: User similarity calculation,rating prediction .
•Performance: Achieved MAE of 5.46 and RMSE of 6.04.
•Embeddings: user feature embeddings.
•Tools: Python, Pandas, Scikit-learn, NumPy.
Data Visualization
1.Overview: The dashboard comprises seven essential pages: Overview, User Analysis, Creator-
wise Analysis, Interaction Analysis, Title Analysis, Rating Analysis, Age-wise Analysis.
2.Objective:
To gain comprehensive insights into user behaviour, content performance, creator impact, and
demographic trends, enabling data-driven strategies for content curation and platform
optimization.
3.Dataset Overview:
The Dataset captures detailed information about users, the media items they interact with, and
the nature of these interactions. Key attributes include:
• User Information: Age, Gender, Location
• Media Item: Title, Type, Genre, Release year, Director/Publisher, Rating, Description
• Interaction Details: Interaction Type (Like, Share, Purchase), Interaction Time
Key Learnings
• Teamwork : We collaborated effectively as a team, leveraging each member's strengths to
complete the project efficiently within the given timeframe.

• Data Analysis: Conducted thorough data analysis to extract valuable insights, which
guided our decision-making process and model development.

• Tech Skills: Gained practical experience with Neural Networks and Machine Learning
techniques, enhancing our technical skills and understanding of advanced algorithms.
Conclusion
Conclusion:

● Successfully developed a recommendation system using collaborative filtering with


demographic-based content.
● Improve the evaluation metrics as per model updation.
● Demonstrated the ability to suggest relevant media based on user demographics.

You might also like