Data-Driven Machine Learning System for Optimization of Processes Supporting the Distribution of Goods and Services – a case study

Tarapata, Zbigniew; Nowicki, Tadeusz; Antkiewicz, Ryszard; Dudziński, Jarosław; Janik, Konrad

doi:10.1016/j.promfg.2020.02.205

Cited by 11 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The flexible process of information system includes several steps such as business process analysis, data flow design and system function setting. From the perspective of information system practice, the flexibility of information system mainly includes three parts: data flexibility, process flexibility and system flexibility, which run through the whole process of information system project [23] [25] [26]. Generally speaking, the good performance of SMIS depends on the normalization of basic data, the institutionalization of business processes and the integration of management systems.…”

Section: Flexibility Of Smismentioning

confidence: 99%

“…This flexible work plan considers error reasons, employee qualifications and product, process and resource data. Zbigniew Tarapata et al [26] put forward a data-driven machine learning system, which can improve the efficiency of the distribution process of goods and services. Tan, BW and Lo, TW [10] took the office automation (OA) system as the research object, and found that customizing the user interface can affect the success of the information system without considering the cognitive style of users.…”

Section: Is Flexibility and Is Performancementioning

confidence: 99%

See 1 more Smart Citation

Customization and Performance of Service-Oriented Manufacturing Information System: The Mediating Effect of Information System Flexibility

Niu¹

2021

IIM

View full text Add to dashboard Cite

The purpose of this paper is to provide empirical evidence for the validity of the relationship between service-oriented manufacturing information system (SMIS) customization and performance from three aspects: data flexibility, process flexibility and system flexibility. We select some questionnaires from the third round of High-performance manufacturing (HPM) data to construct the construct, verify the reliability and validity of the construct, extract principal components, and analyze the mediating effect by using multiple chain linear regression and structural equation model. The results show that SMIS customization has a significant impact on its performance, and this effect works through its flexibility. More specifically, it is the multiple chain mediation effect composed of data flexibility, process flexibility and system flexibility. The importance of SMIS customization and flexibility to the organization is made clear, which helps practitioners understand the internal mechanism that affects SMIS performance, so as to use limited resources to improve system performance.

show abstract

Section: Flexibility Of Smismentioning

confidence: 99%

Section: Is Flexibility and Is Performancementioning

confidence: 99%

Customization and Performance of Service-Oriented Manufacturing Information System: The Mediating Effect of Information System Flexibility

Niu¹

2021

IIM

View full text Add to dashboard Cite

show abstract

“…For example, customers can receive personalized content and product suggestions that could catch the customer interest. The analysis of historical data using machine learning makes it possible to evaluate a variety of factors in order to optimize the choice for suppliers [2,3] and the product-delivery routes for greater logistical efficiency [4,5]. The automated customer segmentation is very useful for maximizing sales, as it allows companies to understand the specific needs of customers and to communicate with them in a personalized way.…”

Section: Introductionmentioning

confidence: 99%

Developing and Preliminary Testing of a Machine Learning-Based Platform for Sales Forecasting Using a Gradient Boosting Approach

Panarese¹,

Settanni²,

Vitti³

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

Organizations engaged in business, regardless of the industry in which they operate, must be able to extract knowledge from the data available to them. Often the volume of customer and supplier data is so large, the use of advanced data mining algorithms is required. In particular, machine learning algorithms make it possible to build predictive models in order to forecast customer demand and, consequently, optimize the management of supplies and warehouse logistics. We base our analysis on the use of the XGBoost as a predictive model, since this is now considered to provide the more efficient implementation of gradient boosting, shown with a numerical comparison. Preliminary tests lead to the conclusion that the XGBoost regression model is more accurate in predicting future sales in terms of various error metrics, such as MSE (Mean Square Error), MAE (Mean Absolute Error), MAPE (Mean Absolute Percentage Error) and WAPE (Weighted Absolute Percentage Error). In particular, the improvement measured in tests using WAPE metric is in the range 15–20%.

show abstract

“…Finally, the concept of automatic sorting was proposed to improve the operation efficiency of logistics. (2) Regarding the aspects of distribution and transportation management, Tarapata et al [7] proposed the use of a data-driven machine learning system supported by the information provided by the Polish National Research and Development Center. They suggested a new method to improve the efficiency of logistics distribution and transportation for Polish transport and logistics service markets.…”

Section: Introductionmentioning

confidence: 99%

“…The value of β can also be any number between 0 and 1, but 0.1, 0.3, 0.5, 0.7, and 0.9 are commonly used to simulate the mental state of a decision maker. A single pair-wise comparison matrix is listed as Equation (7).…”

mentioning

confidence: 99%

Evaluating Pallet Investment Strategy Using Fuzzy Analytic Network Process: A Case in Chinese Chain Supermarkets

Lin

2021

Mathematics

View full text Add to dashboard Cite

Presently in Chinese chain supermarkets, many enterprises have built automatic equipment and information facilities in the logistics center of their supply chain systems. Modern logistics technology and equipment largely depend on the resource integration of each role in the chain (such as suppliers, manufacturers, wholesalers, and retailers), especially logistics facilities and equipment resources, to realize the circulation of products. The pallet, which is an indispensable basic tool for a supply chain system in the process of product circulation, is most often used in the handling, stacking, storage, and transportation of products. The process of building automation and informationization in the supply chain system of Chinese supermarket chains requires the solving of the problems of cost and sharing pallets in logistics operations. Large-scale enterprises often spend millions of dollars on investment, the failure of which can cause significant harm to the enterprise. Therefore, the authors of this paper adopted the fuzzy analytic network process (FANP), combining fuzzy and ANP models to evaluate our studied case. We utilized an actual case as the research object to resolve the important decisions regarding pallet resource sharing investment in the supply chain system. Importantly, it is expected that the proposed method can provide an important reference standard or a new idea for decision makers in the chain supermarket industry or related industries.

show abstract

Data-Driven Machine Learning System for Optimization of Processes Supporting the Distribution of Goods and Services – a case study

Cited by 11 publications

References 7 publications

Customization and Performance of Service-Oriented Manufacturing Information System: The Mediating Effect of Information System Flexibility

Customization and Performance of Service-Oriented Manufacturing Information System: The Mediating Effect of Information System Flexibility

Developing and Preliminary Testing of a Machine Learning-Based Platform for Sales Forecasting Using a Gradient Boosting Approach

Evaluating Pallet Investment Strategy Using Fuzzy Analytic Network Process: A Case in Chinese Chain Supermarkets

Contact Info

Product

Resources

About