Scribd
Upload
4 views12 pages

Restaurant Case Study

This case study analyzes a dataset of over 7,000 restaurants in Bangalore and Pune, focusing on trends, predictions, and insights related to ratings, pricing, and location. The study faced challenges such as inconsistent data and outliers but utilized solutions like a Random Forest regressor and KMeans clustering to derive insights. Key findings suggest strategies for improving delivery in Bangalore and dine-in experiences in Pune, supported by a Power BI dashboard for visualization.

Uploaded by

lekhyareddy29
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
4 views12 pages

Restaurant Case Study

This case study analyzes a dataset of over 7,000 restaurants in Bangalore and Pune, focusing on trends, predictions, and insights related to ratings, pricing, and location. The study faced challenges such as inconsistent data and outliers but utilized solutions like a Random Forest regressor and KMeans clustering to derive insights. Key findings suggest strategies for improving delivery in Bangalore and dine-in experiences in Pune, supported by a Power BI dashboard for visualization.

Uploaded by

lekhyareddy29
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

Restaurant DATA

Case Study

An analytical deep-dive into restaurant data


trends, predictions, and insights
WHAT IS ZOMATO?

• - INDIAN MULTINATIONAL RESTAURANT AGGREGATOR


• - OFFERS FOOD DELIVERY, MENUS, REVIEWS
• - OPERATES IN 24+ COUNTRIES
• - PROVIDES APIS TO ACCESS RESTAURANT INFO
CASE STUDY OVERVIEW

• - DATASET OF 7,000+ RESTAURANTS


• - CITIES: BANGALORE AND PUNE
• - COLUMNS: RATINGS, PRICING, LOCATION, CATEGORY
• - GOAL: PREDICT RATINGS, CLUSTER ZONES, FIND
INSIGHTS
CHALLENGES FACED

• - INCONSISTENT AND MISSING DATA


• - ENCODING COMPLEX TEXT FIELDS
• - UNEQUAL CITY DISTRIBUTIONS
• - OUTLIERS AFFECTING MODEL ACCURACY
SOLUTIONS AND INSIGHTS

• - PREPROCESSED AND ENCODED ALL CATEGORICAL


FIELDS
• - TRAINED RANDOM FOREST REGRESSOR
• - USED KMEANS FOR CLUSTERING
• - BUILT POWER BI DASHBOARD FOR VISUAL TRENDS
STATISTICAL ANALYSIS

• - MODEL: RANDOM FOREST


• - MAE: ~0.23
• - RMSE: ~0.086
• - CLUSTERING: 4 GROUPS VIA KMEANS
EXPLORATORY DATA ANALYSIS
(EDA)
CLUSTERING ANALYSIS
DASHBOARD INSIGHTS
USER TRENDS

• - BANGALORE: HIGHER DINE-IN POPULARITY


• - PUNE: STRONGER DELIVERY PERFORMANCE
• - PRICING TRENDS SHOW MID-RANGE AS MOST RATED
• - CORE AREAS HAVE DENSE HIGH RATINGS
NEW STRATEGIES TO IMPLEMENT

• - FOCUS DELIVERY EXPANSION IN BANGALORE


• - IMPROVE DINE-IN AMBIENCE IN PUNE
• - TARGET HIGH DELIVERY ZONES FOR PROMOTIONS
• - USE CLUSTERS FOR PERSONALIZED MARKETING
CONCLUSION

• - DATA INSIGHTS GUIDE BUSINESS IMPROVEMENTS


• - PREDICTIVE MODELS SUPPORT DECISION-MAKING
• - VISUALIZATION AIDS STAKEHOLDER UNDERSTANDING
• - CASE STUDY DELIVERS ACTIONABLE
RECOMMENDATIONS

You might also like