Problem

⊳ In the used car market, buyers and sellers often struggle to determine a fair price for their vehicles.

⊳ This project aims to provide an accurate and transparent pricing for used cars by analyzing real-world data.


Solution

⊳ Built and deployed an end-to-end ML pipeline to predict used car prices from real-world data.

⊳ Collected and cleaned 2,800+ used car records from Cars24 using Selenium and BeautifulSoup.

⊳ Optimized dataset memory usage by 90% through downcasting data types and converting to Parquet.

⊳ Trained models with Scikit-learn Pipelines & ColumnTransformer to avoid data leakage.

⊳ Deployed the machine learning model as an API using FastAPI on Render.

⊳ Built an HTML/CSS/JS application hosted on GitHub Pages to interact with the API and display predictions.

⊳ Containerized the entire application using Docker and pushed to Docker Hub for reproducibility.


Impact

⊳ Achieved a 30% lower MAE and a 12% higher R2 score compared to the baseline regression model.

⊳ Reduced prediction error variance by 70%, ensuring more stable and reliable predictions.


Result

⊳ Helps car owners quickly find the right selling price for their vehicles based on real-world data.

⊳ Makes it easier for buyers to know if a car is fairly priced before making a purchase.

Problem

⊳ Quick Buy is a leading superstore operating across the United States.

⊳ It manages thousands of product transactions daily across multiple regions.

⊳ The store's operations relied on manual spreadsheets and SQL queries to track business performance.

⊳ As a result, decision-making was slowed down and made it harder to identify growth opportunities.


Solution

⊳ Built an automated ETL pipeline using Python, SQLAlchemy and GitHub Actions for daily data updates.

⊳ Developed Python ETL scripts to extract, transform and load 50,000+ sales records into a Neon database.

⊳ Automated daily data generation (~100 new transactions daily) to simulate real-time sales activity.

⊳ Integrated Power BI with the Neon database, enabling real-time auto-refreshing dashboard.


Key Insights

⊳ Standard Class accounts for ~60% of sales (~₹5.1M) and profit (~₹897K), making it the top shipping mode.

⊳ Consumer Segment generates ~50% of revenue (~₹4.26M) and profit (~₹757K), the primary customer base.

⊳ Q4 (Oct-Dec) contributes ~27% of annual revenue, indicating strong seasonal demand, ideal for marketing.

⊳ Paper, Binders and Phones are the top-performing sub-categories, making up ~45% of total revenue.

⊳ West and East regions lead the market with ~58% of total sales, while South with ~19% has growth potential.

⊳ Top 5 States (CA, NY, TX, PA, OH) contribute ~54% of sales, with CA alone driving ~21% of total sales.


Impact

⊳ Improved daily data update time from hours to under a minute (average ~45 sec) using GitHub Actions.

⊳ Reduced reporting time by 80% through automation, delivering updated insights in under a minute.

⊳ Delivered a reliable, low-latency, fully automated data pipeline with zero manual intervention.

⊳ Achieved 100% workflow reliability, with zero pipeline failures since deployment.

Problem

⊳ With the rise of streaming services, viewers now have access to thousands of movies across platforms.

⊳ As a result, many viewers spend more time browsing than actually watching.

⊳ This problem can lead to frustration, lower satisfaction and reduced watch time on the platform.

⊳ Ultimately, this impacts both user experience and business performance.


Solution

⊳ Built a content-based movie recommender system trained on 5,000+ movie metadata records.

⊳ Generated the top 5 similar titles for any selected movie in under 3 seconds.

⊳ Integrated the TMDB API to dynamically fetch and display movie posters, enhancing user experience.

⊳ Deployed the system as a web app, used by 100+ users to discover personalized movie suggestions.


Impact

⊳ Reduces the time users spend choosing what to watch.

⊳ Increases user engagement, watch time and satisfaction.

⊳ Helps retain users by offering more personalized recommendations.

Problem

⊳ To analyze Netflix content data, uncovering valuable insights into how the platform evolves over time.


Key Findings

⊳ Cleaned and analyzed a dataset of 8,000+ Netflix Movies and TV Shows.

⊳ More than 60% of the content on Netflix is rated for mature audiences.

→ Suggests that Netflix targets adult viewers to boost engagement and retention.

⊳ More than 25% of the Movies and TV Shows were released on the 1st day of the month.

→ Shows a consistent release schedule, likely aligned with subscription renewal cycles.

⊳ More than 40% of the content on Netflix is exclusive to the United States.

→ Shows a strong focus on U.S. market and content availability by location.

⊳ More than 20% of the content on Netflix falls under the "Drama" genre.

→ Confirms that "Drama" is a key part of Netflix's content library.

⊳ More than 23% of the content on Netflix was released in 2019 alone.

→ Indicates a major content push that year, possibly tied to growth or user acquisition efforts.

Problem

⊳ To analyze Supermarket Sales data, identifying key factors for improving profitability and efficiency.


Key Findings

⊳ Analyzed purchasing patterns of 9,000+ customers of a Supermarket.

⊳ More than 15% of the products sold were Snacks.

→ Shows that Snacks are a convenient choice and a major source of revenue.

⊳ More than 32% of total sales came from the West region of the supermarket.

→ Suggests that West region is a strong-performing area as compared to others.

⊳ Health and Soft drinks were the most profitable sub-categories in beverages.

→ Shows that both type of drink options perform well among customers.

⊳ November was the most profitable month contributing about 15% of the total annual profits.

→ Makes it an ideal time for running promotions and special offers.