Fashion Consumer Behaviour
Fashion is very different to the domains where recommender systems originated, both in terms of the industry and in terms of consumer behaviour. In this blog series we examine the main characteristics that make fashion different to other domains, and dive into the challenges that this causes for recommendation algorithms. In our last blog entry we explored different stats to quantify the characteristics of fashion retail, compared with music and movie domains. In this entry we look at user behaviour.
Recommender systems at their core rely on being able to find patterns in user behaviour. For this to be possible…
There’s no showbusiness without the show or the business. Likewise, when it comes to fashion-tech there is no tech without the fashion.
Tech expertise benefits from fashion domain expertise and vice versa. Fashion technology and all the wonders of dazzling customer experiences, storytelling, inspiration and discovery that it affords us may well be the new showbusiness of our time. But fashion is different to movies and other verticals such as music and books. Why we wear what we wear changes. Fashion is emotional and we can switch our tastes as quickly as we blink. In order to cater to these…
Part 1: Fashion Behaviour Data
Fashion is very different to the domains where recommender systems originated, both in terms of the industry and in terms of consumer behaviour. In this blog series we examine the main characteristics that make fashion different to other domains, and dive into the challenges that this causes for recommendation algorithms.
Although recommendation approaches built on and inspired by datasets from Netflix and Spotify have their own interesting characteristics, they do not encounter the conditions specific to the fashion domain, such as the rapidly changing product catalogue and the short lifetime of garments. …
We have always known outfits are at the core of how customers shop. Taking you back to when Dressipi first started, the team, including Style Director, Natalie Theo, took 200 women, who uploaded 30 items from their wardrobe. From these items and 5 new recommended items to update their wardrobe, 20 outfits per customer were created. That is a total of 6000 unique outfits and 1000 new items recommended to update clients’ wardrobes. A huge 75% of these 1000 products were bought.
“If this could be turned into technology that would be pretty amazing.” — Natalie Theo
At Dressipi, we have always known they are an important part of how a customer shops and as fashion consumption moves increasingly online, we needed to replicate this. In the early Dressipi days, outfits were hand-picked by stylists and shown to the customers via weekly emails. It was bi-directional communication where customers could give their feedback, helping to unravel their expectations. As Dressipi grew, this approach became unsustainable and definitely not scalable. …
Whether we realise it or not, at some level we are buying into a version of a fashion trend each season. Some of us more than others.
If you’re reading this right now wearing your favourite sweatshirt you’re more on-trend than you realise. Throw in some sequins and you’ve got one of the key looks for spring/summer covered. Our fashion-specific data allows us to predict just how much of a trend a customer is likely to buy into and when they do we are able to personalise their very own edit of that trend.
A trend is a set of…
Customer Lifetime Value (LTV) and Personalisation, two words that get used a lot by the modern-day marketeer.
There is one obvious tool to deliver on both of those 2 goals: email. Don’t get me wrong, retailers use their email channel. In some cases they send too many emails but, more often than not, they are sending the same manually merchandised products to all customers or, at best, sending segmented emails to their base (bestsellers for men, women, kids etc).
The right communication strategy couples beautiful, branded emails alongside truly personalised and relevant emails. …
It’s no secret that COVID-19 has accelerated the shift to digital commerce within fashion retail. Over the last 12 months, UK womenswear retailers have seen their online revenues increase by an average of 18%.
Another area to deliver a significant boost to the cash position of fashion retailers is the huge drop in return rates for online orders. Womenswear return rates have fallen from an average of 35.4% to 27.8% over the COVID period. This near 8% point (-21%) drop has a huge impact on cash flow and contributed profit. …
As we find ourselves navigating a transformed retail landscape, retailers have been forced to pay microscopic attention to their online capabilities and digital acceleration.
COVID-19, lockdown restrictions, store closures and new social distancing measures in-store have resulted in a much bigger sector of consumers who are more comfortable shopping online than they were before, borne out of necessity and convenience rather than preference. …
“We are coming back to a slightly different world. Sitting on stock, fewer customers, the need to convert our inventory more efficiently and improve bottom line margins.” Stuart Rose, Chairman, Dressipi
At Dressipi we are holding a new series of webinars looking at how data and technology can help to solve some of fashion retailers’ biggest problems. Our first webinar focused on the issue of overstocked products. Stuart highlighted just how different the world of retail is as we come out of lockdown and stressed that it is now essential for retailers to optimise processes.
Due to store closures as…
