Search results

1 – 3 of 3
Per page
102050
Citations:
Loading...
Access Restricted. View access options
Article
Publication date: 14 August 2017

Marko Bohanec, Marko Robnik-Šikonja and Mirjana Kljajić Borštnar

The purpose of this paper is to address the problem of weak acceptance of machine learning (ML) models in business. The proposed framework of top-performing ML models coupled with…

2041

Abstract

Purpose

The purpose of this paper is to address the problem of weak acceptance of machine learning (ML) models in business. The proposed framework of top-performing ML models coupled with general explanation methods provides additional information to the decision-making process. This builds a foundation for sustainable organizational learning.

Design/methodology/approach

To address user acceptance, participatory approach of action design research (ADR) was chosen. The proposed framework is demonstrated on a B2B sales forecasting process in an organizational setting, following cross-industry standard process for data mining (CRISP-DM) methodology.

Findings

The provided ML model explanations efficiently support business decision makers, reduce forecasting error for new sales opportunities, and facilitate discussion about the context of opportunities in the sales team.

Research limitations/implications

The quality and quantity of available data affect the performance of models and explanations.

Practical implications

The application in the real-world company demonstrates the utility of the approach and provides evidence that transparent explanations of ML models contribute to individual and organizational learning.

Social implications

All used methods are available as an open-source software and can improve the acceptance of ML in data-driven decision making.

Originality/value

The proposed framework incorporates existing ML models and general explanation methodology into a decision-making process. To the authors’ knowledge, this is the first attempt to support organizational learning with a framework combining ML explanations, ADR, and data mining methodology based on the CRISP-DM industry standard.

Details

Industrial Management & Data Systems, vol. 117 no. 7
Type: Research Article
ISSN: 0263-5577

Keywords

Access Restricted. View access options
Article
Publication date: 8 June 2015

Masayasu Nagashima, Frederick T. Wehrle, Laoucine Kerbache and Marc Lassagne

This paper aims to empirically analyze how adaptive collaboration in supply chain management impacts demand forecast accuracy in short life-cycle products, depending on…

3384

Abstract

Purpose

This paper aims to empirically analyze how adaptive collaboration in supply chain management impacts demand forecast accuracy in short life-cycle products, depending on collaboration intensity, product life-cycle stage, retailer type and product category.

Design/methodology/approach

The authors assembled a data set of forecasts and sales of 169 still-camera models, made by the same manufacturer and sold by three different retailers in France over five years. Collaboration intensity, coded by collaborative planning forecasting and replenishment level, was used to analyze the main effects and specific interaction effects of all variables using ANOVA and ordered feature evaluation analysis (OFEA).

Findings

The findings lend empirical support to the long-standing assumption that supply chain collaboration intensity increases demand forecast accuracy and that product maturation also increases forecast accuracy even in short life-cycle products. Furthermore, the findings show that it is particularly the lack of collaboration that causes negative effects on forecast accuracy, while positive interaction effects are only found for life cycle stage and product category.

Practical implications

Investment in adaptive supply chain collaboration is shown to increase demand forecast accuracy. However, the choice of collaboration intensity should account for life cycle stage, retailer type and product category.

Originality/value

This paper provides empirical support for the adaptive collaboration concept, exploring not only the actual benefits but also the way it is achieved in the context of innovative products with short life cycles. The authors used a real-world data set and pushed its statistical analysis to a new level of detail using OFEA.

Details

Supply Chain Management: An International Journal, vol. 20 no. 4
Type: Research Article
ISSN: 1359-8546

Keywords

Access Restricted. View access options
Article
Publication date: 2 February 2015

Olivier Mamavi, Haithem Nagati, Gilles Pache and Frederick T. Wehrle

The purpose of this paper is to study if the performance history impacts supplier selection in the French public sector context. While French public procurement legislation…

1601

Abstract

Purpose

The purpose of this paper is to study if the performance history impacts supplier selection in the French public sector context. While French public procurement legislation forbids consideration of the past contract wins in supplier selection, public contractors may still rely on contract win history for highly complex transactions.

Design/methodology/approach

Using French Official Journals (BOAMP), the authors collected all public procurement transactions of 976 suppliers that had at least one transaction per year, over a period of six years (between 2006 and 2011). The authors conducted a two-level hierarchical linear auto-regression analysis and a feature evaluation analysis for all transactions.

Findings

The paper finds significant variation between the transactions of different markets, as well as in the overall positive impact of past wins and in the detailed impact patterns and thresholds of each market. The findings may allow refinement of existing contract awarding strategies and of current legislation.

Originality/value

The paper aims at empirically testing whether a supplier’s degree of success in any given year, measured by the number of public contracts won, may have an impact on the likelihood that the same supplier is awarded a public contract the following year. The authors conclude that suppliers retained for public contracts could benefit from building public buyers’ loyalty using a key account selling approach rather than systematically seeking to acquire new contracts.

Details

Industrial Management & Data Systems, vol. 115 no. 1
Type: Research Article
ISSN: 0263-5577

Keywords

1 – 3 of 3
Per page
102050