Problem Statement: The problem we aim to solve is the intertwined issues of human trafficking and urban crime, particularly in metropolitan areas like New York City. These issues pose significant threats to specific demographics, such as age groups, ethnicities, and genders, who may be unaware of the dangers specific to their backgrounds. The lack of personalized safety information exacerbates these threats. We want to empower individuals with personalized, real-time crime warnings to navigate urban landscapes with confidence and safety. This personalized solution will not only benefit the general public but also aid law enforcement agencies in resource allocation and response. Our goal is to create a safer community for everyone by addressing this complex issue through the Tech for Good theme.
Proposed Solution: Our solution involves developing an algorithmic application that provides personalized crime warnings based on individual characteristics, such as age, ethnicity, and gender. This application will offer real-time, location-specific crime warnings on an interactive map, empowering users to make informed decisions about their safety. The solution utilizes machine learning and data from the NYPD Complaint Dataset to predict danger levels in specific regions in New York, and it prioritizes user privacy and data security. Users can actively contribute to the safety of their community by sharing their real-time experiences and concerns through integrated discussion forums. Additionally, there is a potential collaboration with a volunteering charity, StrutSafe, to offer real people ready to assist those who feel unsafe while walking home.
Audience: Our project's audience includes: a. General public: Individuals of all ages, ethnicities, and genders who want to navigate urban areas safely. b. Law enforcement agencies: Authorities responsible for public safety who can benefit from real-time data for resource allocation and response. c. Insurance companies: Companies interested in offering personalized insurance packages based on travel frequency, location, age group, and gender. d. Small and medium-sized enterprises (SMEs): Businesses interested in creating innovations to protect the public from potential crime while stimulating local commerce. e. Government: Local government authorities interested in improving safety features and reputation management of the city.
Data Sets: For our datathon project, we will primarily use the NYPD Complaint Dataset, which includes crime victim demographics (age, sex, and race) and crime timestamps. This dataset will serve as the foundation for training a machine learning classification model to predict danger levels in specific regions of New York. Additional data may be integrated to enhance the accuracy of our predictions, such as geographical data and external mapping APIs to create a visual representation of crime hotspots on a map.
Log in or sign up for Devpost to join the conversation.