The Journey

From Forevervogue to AtHashtags and TradeSquares.

We started Forevervogue as an experiment spinoff of ManuFracture, an algorithm that aggregated, analysed and recommended content, summarising this content in a way that increased the engagement of the viewer. With Forevervogue, we wanted to narrow the focus, thereby concentrating on lifestyle and fashion. We rewrote the ManuFracture algorithm into AIRED (Aggregation and Analysis, Intuitive Integration, Reviews and Recommendation to Enhance Experience through Data Driven Discovery). The logic was very simple, aggregate trending content from the web, magazines, social media, apps and other sources, analyse the content to determine what type i.e articles, product feed e.t.c find the relationship between the types of content and use that as a basis of personalised recommendation in order to engage the audience for the outcome of them staying longer on the platform or calling to action faster and more reliably. Imagine combining the contrasting features of Facebook and Google, one wants you to spend a lot of time within its platform so it can learn your behaviour, the other wants to be able to find what you need faster hence leaving their platform.

While Forevervogue recommended well, there was a problem it couldn’t solve well and that was making people buy that product recommended that they showed interest in. This was because Forevervogue is article and not product focused. We understood that the same logic of recommendation applies for product as it is for content, however the context has to be product focused, that is it had to be a product recommendation platform.

This is what AtHashtags is; a product recommendation platform that using a derivative of the AIRED algorithm called RETNA and Synapsis to create personalised recommendations for shoppers. The personal recommendations market is indeed an overcrowded one. What makes AtHashtags stand out is unique ability to combine and cross-recommend products from large high street retailers with small exclusive and retailers using the unique machine learning algorithms RETNA and Synapsis.

AtHashtags unique ability to recommend small retailers in the same breath with large retailers is in itself a feat that delves into the heart of retail itself. This is because the processes of small and large retailers are very different for example shoppers trust larger retailers because they are ubiquitous, if they have issues with their online orders, they can always return; usually for free, go in store, call support and so on, all the things that are unaffordable at scale for smaller retailers. These are some of the core reasons shoppers do not trust smaller retailers online.

TradeSquares was launched to help these small retailers (Vendors) list their products on AtHashtags and at the same time have these products physically showcased at physical locations like shops, boutiques and pop up shops. 1 in 3 retailers will feature in pop ups as they are very good avenues for retailers to connect with consumers. TradeSquares increases the functionality of pop ups and stockists by creating an online marketplace to showcase the same items in these multiple pop up shops online so that a shopper can reserve or buy these items online and pick up in a pop up shop closest to them or have the items shipped to their homes.

Items featured in TradeSquares are featured on AtHashtags (so that shoppers can benefit from personalised recommendations of products they need to buy) and Forevervogue (in the heart of content, converting readers into shoppers and vice-versa), placing their products alongside larger retailer products, maximizing exposure while enhancing user experience of personal recommendations made possible through data driven discovery.