People preference for an apparel majorly depends on its design, size and fit in addition to it's affordability and availability. Due to lack of body size data and fit preferences, brands go for a standardized design approach. People struggle to identify the right brand for each of their segment needs.
67% of American women wear a size 14 or above, and most stores /brands don’t carry those numbers. This is primarily due to the traditional thought of desired body size for women as skinny. Enforcing a single set of metrics might make it easier for some of them to shop—like the thinner, white women. But leave out much more than that. Designers turn flat fabric into 3D body coverings in a limited number of sizes and even more limited number of shapes. Fashion industry has had a failed encounter with universal sizing approach due to the much varied shape and size of human body and personal fit preferences. Numeric sizing allows for wider variations in sizes between brands, and changes over time. People struggle to identify the right size in each of the brand. A pair of size-6 jeans can vary in the waistband by as much as 6. Alphawise for Morgan Stanley Research (May 2018) states that 32% like to try the cloth before buying. Online apparel purchase has only made it more challenging. Letting people try the cloth before purchasing through returning is not a sustainable solution. Studies show that about 20-30 per cent of all fashion products bought online are returned. A Morgan Stanley Research findings showed that even a 5% reduction in the rate of product returns could double earnings before income and taxes for an online apparel retailer, all else equal.
Accommodating diverse body sizes has necessitated the brands to start considering much more sizes in its catalog thus requiring good body size feedback and thus push the boundaries of traditional fitting. People's increased preference for customized apparels over standardized designs has necessitated manufacturing 'En mass' standard designs, which have their sizes adapted to fit the individual based on the body measurements. There exists a huge need to study data from across the user category to help better understand people who have the same clothing size but are different body shapes to improve sizing garment specifications. Existing tech solutions addressing sizing problem employs recommendation systems based on similar sized people purchase/return patterns. However people with similar body measurements and fit preferences do not necessarily have the same taste in design, style and color preferences thus posing difficulties in getting the perfect match. While 3D body scanning has been around for years, the technology for mobile systems is not yet able to reach a satisfactory level of accuracy and reliability
BM makes a direct match between the user and the corresponding fit based on user body measurements and candidate apparels measurements. Recommendations are personalized for each user and is able to suggest the right apparel candidates for each user across brands that have clothes as per the user's preference of size, fit and design. BM body scanning is a non-contact 3D measurement system that uses infrared depth sensing and imaging technology to produce a digital copy of the surface geometry of the human body. BM uses the accurate body measurements of the user using portable and simple to use body scan technology to provide the nearest matching apparel recommendations. Existing sizing solutions like True fit, Fit analytics and Chloe of Le Tote lack the true body size measurements needed to make accurate recommendations. Further, they make the sizing recommendations based on user provided inputs such as height, weight and fit preferences that are trivial to provide good matching recommendations. Few other tools are asking the user to provide information on their body size measurements using tape measure which can lead to high margin of error and user discomfort.
BM body scan technology can accurately measure up to 100 body size parameters in less than a minute. It's deep learning algorithms take user feedback for apparel fit to learn and make improvised body measurements in consecutive uses.
BM creates an immersive shopping experience for online purchasers. It facilitates virtual fit assessment through letting the user try different apparels over his/her virtual avatar. The direct size based recommendations eliminates the returns due to fitting or size mismatches thus creating a shopping experience as close as in stores. BM enhances the in-store shopping experience by letting users focus more on designs rather than spending time in trial rooms. The purpose of project is to do experimental development comprising of prototyping, demonstrating, piloting, testing and validation of new product in environments representative of real life environment for the proposed innovation