Homesharing website
Providing higher-quality recommendations to users, converting new and current users onto new platforms, and incorporating group recommendations on the platform
Facing a constantly increasing number of competitors in the field, HSW is a modern and innovative business looking for ways to differentiate themselves further from their competition. HSW is looking to not only provide its users with a stay that is delightful and aligned with their users taste, but they are also diversifying their product offering by merging experiences in local activities and dining to provide new features for their users. By doing so, they hope to increase their organic growth.
The challenges
HSW is the perfect example of how businesses are now migrating from “Search Engine” to “Recommendation” as the main algorithm to power their businesses. HSW’s limitation is that to search, it requires a user to enter a set of filters (location, number of guests, pricing) and then the user receives a list of stays satisfying the filters only. Unfortunately for HSW users, results are not personalized so every user sees the same results regardless of their historical transactions. This in itself creates frustration and churn.
The biggest challenge HSW had was their extremely sparse dataset, which was why their traditional approach and tools for recommendations were currently failing their users. Another challenge HSW faced was their goal of diversifying their product offering. When HSW decided to add “Experiences” and “Restaurants” to their platform, it led the company to creating three different Machine Learning teams in order to tackle each recommendation algorithm for each domain. Additionally, one of the struggles of HSW was getting their existing customers to use their new products.
Our approach
Crossing Minds and HSW settled on tackling these three challenges with the goal of increasing HSW’s organic growth by:
- Providing higher quality recommendations to their users based on taste-mapping.
- Leveraging cross-domain information to convert more of their users to their new product offerings.
- Incorporate group-recommendations into their platform for the first time.
For Crossing Minds, the solution here was to unify those three products by providing cross-domain recommendations, which we accomplished by using our Hai tool. Hai allowed us to merge user data from all three products to create a seamless experience across HSW’s entire site which also resolved the issue of getting current customers and new customers to use the new products. Crossing Minds algorithm is built for extremely sparse data, and we were able to demonstrate a significant improvement in recommendation accuracy compared to HSW’s previous methods.
Results
An additional benefit to HSW using cross-domain recommendations on their platform was the increased number of referrals the users sent out from within the HSW platform. It turned out that the benefits of finding the perfect stay for an entire group was the incentive users needed to invite their friends onto the platform to create accounts and participate.
In conclusion, it was confirmed through the use of Hai on the HSW platform, that the deep learning techniques Hai employed allowed a significant breakthrough for recommendation accuracy when it came to employing cross-domain recommendation. Another deduction that had been demonstrated was that the strategy of building a recommender system with a domain-agnostic approach was considerably more insightful and powerful.
Therefore, Crossing Minds was able to add distinct differentiators to the HSW platform by:
- Creating user-recommendations that are now more accurate leading to higher conversions.
- Allowing HSW to leverage information from one domain to another by using cross-recommendation systems.
- Integrating group-recommendations into HSW’s platform with the purpose of differentiating them from their competition while simultaneously increasing their organic growth and revenue.
Work with us to improve your consumers conversion