I wonder if there is a minimum of traffic or conversion needed for Recommendations to work well?
For Recommendations to work effectively/develop its algorithm is there any guideline or documentation specifically looking at the sales/conversion volumes required for the machine learning to work?
It's totally depending on which alogos you use. There are some algos require no traffic like content similarity algo, also a custom curated algo that they can upload into Target’s ecosystem, and recently viewed algo as well.
Recently viewed and popularity algos require little traffic. Also if the customer has their own offline bought-this-bought-that data they can use a custom algo that they upload into Target (if there are not many online purchases happening). If so, the customer can avoid a 'cold start' and deliver relevant recommendations immediately.
It's totally depending on which alogos you use. There are some algos require no traffic like content similarity algo, also a custom curated algo that they can upload into Target’s ecosystem, and recently viewed algo as well.
Recently viewed and popularity algos require little traffic. Also if the customer has their own offline bought-this-bought-that data they can use a custom algo that they upload into Target (if there are not many online purchases happening). If so, the customer can avoid a 'cold start' and deliver relevant recommendations immediately.
Would you know were I can find examples of how banks or financial services are using Recommendations? Which algo would be best for them as the do not really have a catalogu but rather 5-10 "products" with different flavours (ex. credit card S, M, L, XL...)
