Machine learning based inventory optimization respecting supplier order line fees

Abstract: This thesis addresses an inventory management problem of what, when and how many products should be ordered from the supplier applying order line fees. Order line fee is a fixed fee which the company pays to the supplier per every ordered product not depending on the ordered quantity. Even though there are various inventory management methods and variety of research done in the field, there was no research found related to inventory management when supplier order line fees are applied. The described problem is real and currently exists at the company ASWO Baltic. The problem is solved by using experimental research method and CRISP-DM process. The historical company’s data of customer and supplier orders is used for the project. Data is analyzed and prepared for model creation by using feature engineering, data transformation and data normalization methods. Min/Max inventory management method is used as a base for model creation. The improvement proposed by the thesis is to use machine learning algorithms to predict Min and Max stock levels. Support Vector Regression, k-nearest neighbors, Random Forest, Artificial Neural Network, ARIMA, and Prophet machine learning algorithms are tested both for Min and Max level prediction. It was found out that the best results for Min stock level prediction were achieved by k-nearest neighbors algorithm with the average sMAPE measure of 7.0079%. The best predictions for Max stock level were done by Random Forest algorithm with the average sMAPE of 15.0303%. After the hyperparameter optimization sMAPE was improved to 6.8730% and 14.6813% accordingly. The simulation was run to evaluate if the proposed algorithm outperforms the current system. It showed that for the items which have more than 200 orders the algorithm decreased the number of supplier orders by 35,83% and the number of backorders by 49,29% while keeping almost the same inventory turnover. If the same results are achieved with the all products, it is expected that the company would save around 60K euros per annum on supplier order line fees and the lower number of backorders would increase sales by 24%.