Developing Data-Conscious Deep Learning Models for Product Classification

Kim, Yijin; Lee, Hong Joo; Shim, Junho

doi:10.3390/app11125694

Cited by 7 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Trying to combine information from different sources can lead to increased resource consumption and errors, causing problems in deliveries, invoicing, inventory management, and transportation planning [4,50]. Increased awareness of problems regarding data management initiated Master Data Management (MDM) trends, in which a company's data are managed in a centralised manner, using a set of tools and processes for information systems standardisation (record data only once) and integration, and for data quality [50,51], whereas automated product classification is introduced to reduce human error [52,53]. These processes ensure data consistency and enable control of data usage for different operational and analytical applications.…”

Section: Demystification Of Product Master Data and Logistic Datamentioning

confidence: 99%

Impact of the Product Master Data Quality on the Logistics Process Performance

Božić,

Živičnjak,

Stanković

et al. 2024

Logistics

View full text Add to dashboard Cite

Background: The importance of up-to-date product master data in the digital age should not be underestimated. However, companies still struggle to ensure high-quality product data, especially in the field of logistics. Hence, the focus of our research lies in the disregard of the importance of product data quality to the performance of logistics processes. Methods: The analysis of the influence of product data on the performance of logistics processes was carried out using data from two fast-moving consumer goods (FMCG) distribution and retail companies. Data were gathered via interviews, while process activities were timed using a stopwatch, and interruptions were documented. The significance of the impact was determined using inferential statistical procedures based on the variable and the measurement scale type employed. Results: The quality of product master data has a significant impact on the performance of logistics processes; while managers are aware of the complications, they lack the motivation to detect and analyse such inaccuracies. Conclusion: The findings enhance comprehension of the obstacles generated by inadequate product data in logistics, which obstruct optimisation, and offer numerical proof of the impact of product data quality on logistics performance, thus expanding the current body of research.

show abstract

Section: Demystification Of Product Master Data and Logistic Datamentioning

confidence: 99%

Impact of the Product Master Data Quality on the Logistics Process Performance

Božić,

Živičnjak,

Stanković

et al. 2024

Logistics

View full text Add to dashboard Cite

show abstract

“…It is difficult to mine information from the existing feature dimensions because the dataset includes users, commodities, commodity categories, user behavior types, operation time, and other data [20]. erefore, in order to better mine useful information from data, the 107 features of counting class, sorting class, time difference class, and conversion rate class are selected from the aspects, such as commodities, commodity categories, user-commodity interaction, user-commodity category interaction, and commodity-commodity category interaction, to construct the model [21,22]. e characteristics of each category and their meanings are shown in Table 5.…”

Section: Feature Extractionmentioning

confidence: 99%

Data Analysis and Prediction Modeling Based on Deep Learning in E-Commerce

Feng

2022

Scientific Programming

View full text Add to dashboard Cite

Due to the low efficiency of traditional data analysis methods for massive e-commerce data analysis, an e-commerce data analysis and prediction method based on the GBDT deep learning model was proposed. Purchase behavior is divided into another category, which transforms the problem of e-commerce data analysis and prediction into a binary classification problem. At the same time, we extract 107 features that can reflect the user behavior and construct the GBDT model. The characteristics include counting class, sorting class, time difference class, conversion rate class, and so on. It follows from the above that the analysis and prediction of e-commerce data are realized. In addition, the results show that when the learning rate of GBDT model parameters is 0.05, the number of basic learners is 200, the tree depth is 20, the threshold is 0.5, the model prediction effect is best, and the F1 value can reach 0.12. Compared with the traditional prediction model based on logistic regression and neural network, the proposed GBDT model is more suitable for e-commerce data analysis and prediction.

show abstract

“…Its applications mainly concentrate on the improvement of computer programs that can able to obtain data and employ it to absorb personally [7]. During the last year, deep learning (DL) particularly in the area of computer vision (CV) has attained wonderful achievement and become the fundamental solution for object recognition and image identification [8]. The main alteration among DL and customary pattern detection techniques is can previously acquire features in image data directly instead of utilizing physically intended features [9].…”

Section: Introductionmentioning

confidence: 99%

Empowering Retail Through Advanced Consumer Product Recognition Using Aquila Optimization Algorithm With Deep Learning

Alghamdi,

Mengash,

Aljebreen

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Recently, consumer product recognition comprises harnessing cutting-edge technologies namely artificial intelligence (AI) and computer vision (CV) to develop the purchasing expedition. This technology allows retailers to utilize robust product recognition systems that precisely identify and categorize products in real time. The comprehension of automatic product identification becomes of major importance for both social and economic improvement since it is more reliable and time-consuming than manual function. Product detection through images is a complex task in the domain of CV. This can be obtained the improving consideration because of the excellent application viewpoint like visually impaired assistance, stock tracking, automatic checkout, and planogram compliance. Currently, deep learning (DL) prefers a successful progression with great achievements in object detection and image classification. Therefore, this study presents Advanced Consumer Product Recognition using the Aquila Optimization Algorithm with Deep Learning (ACPR-AOADL) technique. The proposed ACPR-AOADL model utilizes hyperparameter-tuned DL concepts for the identification of consumer products. To achieve this, the ACPR-AOADL model first pre-processes the input data utilizing a Wiener filter (WF) to improve the image quality. Besides, the YOLO-v8 model with a deep residual network (DRN) as a backbone network can be applied for the product detection process. For product classification, the deep belief network (DBN) approach can be used. To boost the complete product detection process, the ACPR-AOADL technique involves AOA based hyperparameter selection process. The performance analysis of the ACPR-AOADL method can be examined under the Product-10K dataset. Wide-ranging results stated that the ACPR-AOADL technique reaches enhanced classification performance over other compared approaches.

show abstract

Developing Data-Conscious Deep Learning Models for Product Classification

Cited by 7 publications

References 17 publications

Impact of the Product Master Data Quality on the Logistics Process Performance

Impact of the Product Master Data Quality on the Logistics Process Performance

Data Analysis and Prediction Modeling Based on Deep Learning in E-Commerce

Empowering Retail Through Advanced Consumer Product Recognition Using Aquila Optimization Algorithm With Deep Learning

Contact Info

Product

Resources

About