Our Technology
Download Case Study

Presize proved to be 55% more accurate than direct competitors

September 15, 2020

State of the market  

The B2B software market for size recommendation software consists of various players with different solutions. To determine the right size of clothing for customers, there are many different approaches. First there are picture- and app-based solutions. They often require downloads and only produce grey and generic body visualizations. Due to the limitation of only having one side view and one frontal view, they are prone to errors resulting from small changes in posture or clothing, which leads to low accuracy and robustness.  

The Accuracy Benchmarking  

Benchmark: We benchmarked against various solutions and focused on the solution that delivered the 2nd highest accuracy after Presize in the benchmarking. The competing solutions rely on two pictures (front view and side view).

Setup:  For the benchmarking, the same input data was given to the Presize algorithm and the competitors' algorithms. It is data from real users and not produced in a lab environment.

Sample: 255 subjects with a mix of tight clothing, everyday clothing and demographics (weight/age).

Ground truth: Body measurements from professional tailors who manually measured each subject according to the same ISO standard.

Results:                  
MAPE = Mean Absolute Percentage Error (deviation from ground truth in %)

Over all 255 subjects:

90% of subjects had a lower MAPE with Presize

55% lower MAPE with Presize  

For the 99 subjects in tight clothing:

94% of subjects had a lower MAPE with Presize

67% lower MAPE with Presize

Here are some visual examples on where Presize delivers good results while the competing solutions fail:

The results of the accuracy benchmarking

Important

We combine up to 6 body measurements into one size recommendation. For example, if chest circumference is off 1 cm for a t-shirt, it is very unlikely that all measurements (belly, shoulders, hips, arms…) are off and that they deviate in the same direction which would result in a wrong size recommendation. 

Interpretation

Just like the rest of the competition, the competitors require the user to take two pictures to predict body measurements. This lacks a 360° view of the body (unlike our video approach) and makes it impossible to deal with occlusions and regular clothing. If you are looking for a solution that combines high convenience (recording a video is optional, good results in regular clothing and imperfect poses, no app download needed) and high accuracy, Presize is the right choice.        

‍Use Presize for your advantage
Raban Siegler
Growth Manager
Copyright © 2021 Presize GmbH
Made with ♡ in Munich, Germany