Creating a Back Stock to Increase Order Delivery and Pickup Availability

Abstract: Apotek Hjärtat wants to keep developing their e-commerce website and improve retrieval and delivery of orders to customers. Click and Collect and Click and Express are two options for retrieving e-commerce orders that are available if all products in the order are present in the store. By implementing a back stock in the stores with popular e-commercial items, all products of an order will more often be present in the store. The back stock will in such a way increase the availability of Click and Collect and Click and Express. The goals for the study are to conduct a pilot study, compare methods and possible solutions to implement a model to reach the goals. The pilot study was made by studying previous works in mathematical statistics methods and machine learning methods. The statistical method was accomplished through the analytical tool Statistical Package for the Social Sciences (SPSS) and Java. The machine learning method was accomplished through Python and the Scikit-learn library. The machine learning method was performed by a regression algorithm that was used to find relations between category sales and pollen forecasts. The statistical and machine learning methods were compared to each other. Both gave identical results, but the machine learning method was more functional and easier to further develop and consequently was chosen. Several models were created for a few selected product categories. The categories that did not work for the models had an unrealistic amount of sold products. These amounts could be negative or extremely high when unknown inputs were introduced. A simulation was made of the back stock to estimate how it would increase the availability of Click and Collect/Click and Express. The machine learning models could need more data for more accurate predictions. A conclusion could be made though that is possible to predict the amount of sold products of certain categories such as Allergy and Child Medicine with pollen halt taken into account.