Data-Driven Insights for FoodHub’s Restaurant Demand Analysis

As part of MIT’s Institute for Data, Systems, and Society (IDSS) program in Data Science and Machine Learning, I undertook a project focused on enhancing the customer experience for FoodHub, a prominent food aggregator company in New York. The city’s burgeoning restaurant scene and the fast-paced lifestyles of students and professionals have made online food delivery services increasingly popular. FoodHub’s smartphone app acts as a gateway, connecting customers with various restaurants. The project aimed to leverage Python, utilizing the pandas and numpy libraries for data manipulation, and matplotlib along with seaborn for data visualization.

The objective was to analyze the extensive dataset comprising information on different food orders made through the FoodHub app. In the role of a Data Scientist within the company, the goal was to answer key questions identified by the Data Science team to improve business operations. The dataset included essential details such as order ID, customer ID, restaurant name, cuisine type, order cost, day of the week, customer rating, food preparation time, and delivery time. These details enabled me to provide valuable insights into restaurant demand, helping FoodHub enhance its services.

The analysis involved exploring customer behavior, understanding popular cuisines, assessing delivery and preparation times, and identifying trends based on weekdays and weekends. The findings not only shed light on customer preferences but also guided strategic decisions to improve the overall efficiency of FoodHub’s operations. Python’s versatile capabilities, coupled with the rich data set, empowered me to derive actionable recommendations for the company’s continued success in the competitive food delivery market.

The code for this case study can be found in my Kaggle profile.

Skills & Tools

Exploratory Data Analysis, Data Visualization, Statistics, Python, Pandas, NumPy, Seaborn, Matplotlib