Predictive Pricing Model for Airbnb Properties
The project tackled the business problem of identifying the most optimal investment strategy for acquiring, restoring, and listing old buildings on Airbnb. Utilizing Python and Machine Learning techniques, a linear regression as well as a clustering model was developed with data scraped from the Airbnb website. These models aimed to pinpoint the most influential features of apartments contributing to higher prices and inform strategic decision-making to maximise retrun on investment.
Tools used: Python, Machine Learning
Identified key factors influencing Airbnb listing prices with Machine Learning
Analysing NYPD 'Stop, Question and Frisk' Data
This project entails exploring the NYPD 'Stop, Question and Frisk' database, with a focus on downloading, inspecting, and preparing the data for analysis using the Pandas library. The preparation phase involves meticulously examining and modifying the dataset to ensure coherence and integrity for subsequent analysis. The ultimate goal is to analyze the data to uncover insights into the contentious stop-and-frisk program, shedding light on its implications and potential biases.
Tool used: Python
Prepared and merged sizable year-wise datasets for analysis of NYPD's program
Marvel Characters Database Creation
The project involved the creation of a Marvel database, using the Beautiful Soup library in Python to extract character data from Marvel's API. This process facilitated the compilation of a comprehensive database containing general information and powers of the characters. Additionally, the database could be customized to include characters from users' favorite selected series.
Tool used: Python
Built a Python database by connecting to the Marvel API
