[u' @inproceedings{benhamida_stockbuy_2020, address = {Split (Croatia)}, title = {Stock\\&{Buy}: {A} {New} {Demand} {Forecasting} {Tool} {For} {Inventory} {Control}}, shorttitle = {Stock\\&{Buy}}, url = {https://ieeexplore.ieee.org/abstract/document/9243824}, doi = {10.23919/SpliTech49282.2020.9243824}, abstract = {Demand forecasting is playing a crucial role for many retail firms where effective inventory management allows accurate balance between demands and offers. One of the most common methods for demand forecasting is by analyzing previous data to help predicting future demands/supplies. This work presents a growing online retail platform, Stock\\&Buy, to integrate a demand forecasting tool. First, a forecasting pipeline is designed where extensive literature review and pre-analyzing data allowed to make the most appropriate decisions to reach high accuracy. After that, a new demand-forecasting tool, Comb-TSB, is proposed for intermittent and lumpy demand patterns. Comb-TSB automatically selects the most accurate model among a set of methods. Besides, a clustering-based approach (ClustAvg) is proposed to forecast demand for new products which have very few or no sales history data. The evaluation process showed that the proposed tool achieves good forecasting accuracy by making the most appropriate choice while defining the forecasting method to apply for each product selection.}, booktitle = {In 2020 5th {International} {Conference} on {Smart} and {Sustainable} {Technologies} ({SpliTech})}, publisher = {IEEE Xplore}, author = {Benhamida, Fatima Zohra and Kaddouri, Ouahiba and Ouhrouche, Tahar and Benaichouche, Mohamed and Casado-Mansilla, Diego and L\xf3pez de Ipi\xf1a, Diego}, month = sep, year = {2020}, keywords = {Forecasting, IoT}, pages = {1--6}, } ']