Predicting the resale value of a car is not a simple task. The value of used cars depends on a number of factors. The most important ones are usually the age of the car, its model, the origin of the car, manufacturer, its mileage and its horsepower. Due to rising fuel prices, fuel economy is also of prime importance.
Unfortunately, in reality, most people do not know exactly how much fuel their car consumes for each km driven. Other factors such as the type of fuel it uses, the interior style, the braking system, acceleration, the volume of its cylinders (measured in cc), safety index, its size, number of doors, paint colour, weight of the car, consumer reviews, prestigious awards won by the car manufacturer, its physical state, whether it is a sports car, whether it has cruise control, whether it is automatic or manual transmission, whether it belonged to an individual or a company and other options such as air conditioner, sound system, power steering, cosmic wheels, GPS navigator all may influence the price as well. The look and feel of the car certainly contributes a lot to the price. As mentioned, the price depends on a large number of factors, but Unfortunately, information about all these factors are not always available, which forces buyer to make the decision few factors only.
There has been a lot of work in the Economics and Data Mining community on analyzing online auctions. Most of this work has focused on describing past auctions rather than prediction. Cognub has come up with an advanced machine learning techniques which considers all the mentioned factors with the available auction datasets to predict auction trends patterns and the price (artificial neural networks, fuzzy logic and genetic algorithms). With the help of these techniques it can build models on bidding behavior and predict the factors that affect the price. By using web crawler it can extract auction listing and make inferences about the general patterns about the auctions and also to predict auction outcomes and car prices. Alongside this it will also support buying recommendations, listing optimization and Price Estimation for Complimentary Services.