This project presents a Python-based system for dynamic pricing and demand forecasting for car rentals
, focusing on improving price accuracy, operational efficiency, and data-driven decision-making. Car
rental agencies often struggle with setting optimal rental prices due to varying factors such as vehicle
type, age, mileage, location, demand fluctuations, and customer usage patterns. To address this, the
proposed system integrates data collection, preprocessing, analysis, rule-based training, and a user
interface into a complete pricing workflow. In the existing system, rental prices are generally determined
manually based on fixed charts, staff experience, or broad assumptions about market demand. These
static methods do not evaluate historical trends, do not adapt to seasonal or regional variations, and
cannot analyze multiple influencing factors simultaneously. As a result, pricing becomes inconsistent,
less competitive, and may lead to revenue loss or customer dissatisfaction. Demand forecasting is also
rarely automated, leaving agencies unable to predict which vehicles will be in high demand at specific
times. The proposed system overcomes these limitations using a structured Python-based pipeline. First,
historical rental datasets are collected and loaded into Python.
