AAI_2025_Capstone_Chronicles_Combined

Cinema Analytics and Prediction System

2

Introduction

In an era where data drives decision-making across industries, the film sector is no

exception. The Capstone Project titled "Cinema Analytics and Prediction System" explores how

artificial intelligence, specifically machine learning (ML) and deep learning (DL), can be

harnessed to decode the complex dynamics of Hollywood cinema. By analyzing a

comprehensive dataset this project aims to build a predictive and recommendation engine that

can forecast box office revenue, assess commercial success, classify genres from plot

summaries, and suggest similar movies using content-based filtering.

The project addresses key questions that are vital to both industry stakeholders and

consumers: How much revenue will a movie generate? Will it be a hit or a miss? What genres

best describe their storyline? And what other films might appeal to the same audience? These

insights are not only valuable for studios and streaming platforms but also for market analysts

and movie enthusiasts seeking data-driven perspectives.

By integrating structured metadata with unstructured textual content and leveraging

APIs like IMDb and TMDb for real-time scalability, this initiative demonstrates the

transformative potential of AI in creative domains. We present a modular system composed of

four main components: movie revenue prediction, success classification, genre classification,

and content-based recommendation. The current implementation emphasizes model

development and evaluation to perform standalone analytical tasks but also to function as

building blocks for a future production-ready system. Looking ahead, the models and pipelines

developed in this project can be integrated into a larger-scale platform equipped with data

169

Internal