Avto.ru launched a neural network to analyze the condition of a car from a photo and determine its price. This was reported to RB.RU by the company’s press service.
Join
The neural network analyzes the condition of a used car using photographs of the interior and exterior. Select the necessary angles, then the ML algorithm reacts to defects on the body and interior: scratches, abrasions, chips and traces of poor-quality repairs or corrosion.
After this, the car receives a condition category from excellent to poor, which is taken into account when creating a fair price forecast. The algorithm helped improve the accuracy of estimating the cost of cars, which is important for cars in poor condition, since their cost compared to a similar model in excellent condition can differ by 15% or more.
Thanks to neural network analysis, all Avto.ru users will be able to see an estimate of the fair value of the car, taking into account its condition. Only offers for damaged cars, which represent a small percentage of the total, are excluded from the control.
The new neural network is also integrated into the Avto.ru Business service, which allows professional car buyers to view the condition evaluation in the purchasing section within the dealer’s personal account, as well as on the card of a specific car . Currently, photo-based condition evaluation is available only for offers published on Avto.ru.
Author:
Karina Pardaeva
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
