Smart basket recommendations for online selections

A method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media, the method comprising:

• tracking respective duration data for each respective item of items in a catalog based on purchase histories of the each respective item by users, the respective duration data measuring a reorder rate for the each respective item within one or more first periods of time;
• generating a Weibull distribution for the each respective item using the respective duration data for the each respective item;
• training a machine learning model based on previous orders by the users, such that, for each respective order of the previous orders by a respective user of the users, (a) input data for the machine learning model comprises the Weibull distribution for the each respective item of the items, brand affinities for the respective user, and product type affinities for the respective user, and (b) output data for the machine learning model comprises respective indications of whether the respective user ordered the each respective item, respective quantities associated with the each respective item, and a basket size of the each respective order;
• generating, using the machine learning model, as trained, a ranked list of one or more first items for a user of the users, a respective predicted quantity for each of the one or more first items, and an average basket size for the user, wherein the items comprise the one or more first items;
• receiving a request for recommended items from the user using a user interface provided by a retailer;
• and
• responsive to the request, sending the ranked list of the one or more first items to be displayed on the user interface.