toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Records Links
Author Rozas Andaur, J.M.; Ruz, G.A.; Goycoolea, M. doi  openurl
  Title Predicting Out-of-Stock Using Machine Learning: An Application in a Retail Packaged Foods Manufacturing Company Type
  Year 2021 Publication Electronics Abbreviated Journal Electronics  
  Volume 10 Issue 22 Pages 2787  
  Keywords out of stock; machine learning; classification algorithms; imbalance data; supply chain management; decision support; retail industry application  
  Abstract For decades, Out-of-Stock (OOS) events have been a problem for retailers and manufacturers. In grocery retailing, an OOS event is used to characterize the condition in which customers do not find a certain commodity while attempting to buy it. This paper focuses on addressing this problem from a manufacturer’s perspective, conducting a case study in a retail packaged foods manufacturing company located in Latin America. We developed two machine learning based systems to detect OOS events automatically. The first is based on a single Random Forest classifier with balanced data, and the second is an ensemble of six different classification algorithms. We used transactional data from the manufacturer information system and physical audits. The novelty of this work is our use of new predictor variables of OOS events. The system was successfully implemented and tested in a retail packaged foods manufacturer company. By incorporating the new predictive variables in our Random Forest and Ensemble classifier, we were able to improve their system’s predictive power. In particular, the Random Forest classifier presented the best performance in a real-world setting, achieving a detection precision of 72% and identifying 68% of the total OOS events. Finally, the incorporation of our new predictor variables allowed us to improve the performance of the Random Forest by 0.24 points in the F-measure.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 2079-9292 ISBN Medium  
  Area Expedition Conference  
  Notes Approved  
  Call Number UAI @ alexi.delcanto @ Serial 1487  
Permanent link to this record
 

 
Author Sandoval, G.; Alvarez-Miranda, E.; Pereira, J.; Rios-Mercado, R.Z.; Diaz, J.A. doi  openurl
  Title A novel districting design approach for on-time last-mile delivery: An application on an express postal company Type
  Year 2022 Publication Omega-International Journal Of Management Science Abbreviated Journal Omega-Int. J. Manage. Sci.  
  Volume 113 Issue Pages 102687  
  Keywords Districting; Last-mile delivery; Postal delivery; Supply chain management; Heuristics  
  Abstract Last-mile logistics corresponds to the last leg of the supply chain, i.e., the delivery of goods to final cus-tomers, and they comprise the core activities of postal and courier companies. Because of their role in the supply chain, last-mile operations are critical for the perception of customers regarding the perfor-mance of the whole logistic process. In this sense, the sustained growth of e-commerce, which has been abruptly catalyzed by the irruption of the COVID-19 pandemic, has hanged the habits of customers and overtaxed the operational side of delivery companies, hindering their viability and forcing their adap-tation to the novel conditions. Many of these habits will remain after we overcome the sanitary crisis, which will permanently reshape the structure and emphasis of postal supply chains, demanding compa-nies to implement organizational and operational changes to adapt to these new challenges. In this work we address a last-mile logistic design problem faced by a courier and delivery company in Chile, although the same problem is likely to arise in the last-mile delivery operation of other postal companies, in particular in the operation of express delivery services. The operational structure of the company is based on the division of an urban area into smaller territories (districts) and the outsourcing of the delivery operation of each territory to a last-mile contractor. Because of the increasing volume of postal traffic and a decreasing performance of the service, in particular for the case of express deliveries, the company is forced to redesign its current territorial arrangement. Such redesign results in a novel optimization problem that resembles a classical districting problem with the additional quality of service requirements. This novel problem is first formulated as a mathematical programming model and then a specially tailored heuristic is designed for solving it. The proposed approach is tested on instances from the real-life case study, and the obtained results show significant improvements in terms of the percent-age of on-time deliveries achieved by the proposed solution when compared to the current districting design of the company. By performing a sensitivity analysis considering different levels of demand, we show that the proposed approach is effective in providing districting designs capable of enduring signifi-cant increases in the demand for express postal services.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 0305-0483 ISBN Medium  
  Area Expedition Conference  
  Notes WOS:000809666900001 Approved  
  Call Number UAI @ alexi.delcanto @ Serial 1605  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: