Quality Analysis of Shopee Seller Portal by Using Category Recommendation System Approach

Thwe, Yamin; Tungkasthan, Anucha; Jongsawat, Nipat

doi:10.1109/ictke52386.2021.9665701

Cited by 2 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The preceding paper [6] examined the system's fault in automatic category recommendations on the Shopee Thailand E-commerce portal. This research can assist buyers in avoiding seller fraud and determining which categories are frequently mis-selected by vendors, particularly in the fashion area.…”

Section: Introductionmentioning

confidence: 99%

“…We will concentrate on the Shopee E-commerce platform, which ranks highly among the most powerful E-commerce platforms in the consumer base. Even when the system recommends products for the category in the Shopee seller portal, sellers continue to make category errors, especially the fashion product [6]. Therefore, we will use FC-YOLOv4 to automatically recognize the product category, assisting merchants in making the best selection which is a crucial aspect of E-commerce business intelligence.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Semi-Supervised Learning Approach for Automatic Detection and Fashion Product Category Prediction with Small Training Dataset Using FC-YOLOv4

2022

Self Cite

View full text Add to dashboard Cite

Over the past few decades, research on object detection has developed rapidly, one of which can be seen in the fashion industry. Fast and accurate detection of an E-commerce fashion product is crucial to choosing the appropriate category. Nowadays, both new and second-hand clothing is provided by E-commerce sites for purchase. Therefore, when categorizing fashion clothing, it is essential to categorize it precisely, regardless of the cluttered background. We present recently acquired tiny product images with various resolutions, sizes, and positions datasets from the Shopee E-commerce (Thailand) website. This paper also proposes the Fashion Category—You Only Look Once version 4 model called FC-YOLOv4 for detecting multiclass fashion products. We used the semi-supervised learning approach to reduce image labeling time, and the number of resulting images is then increased through image augmentation. This approach results in reasonable Average Precision (AP), Mean Average Precision (mAP), True or False Positive (TP/FP), Recall, Intersection over Union (IoU), and reliable object detection. According to experimental findings, our model increases the mAP by 0.07 percent and 40.2 percent increment compared to the original YOLOv4 and YOLOv3. Experimental findings from our FC-YOLOv4 model demonstrate that it can effectively provide accurate fashion category detection for properly captured and clutter images compared to the YOLOv4 and YOLOv3 models.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Semi-Supervised Learning Approach for Automatic Detection and Fashion Product Category Prediction with Small Training Dataset Using FC-YOLOv4

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, limited studies have attempted to analyse the fraud threats in the Shopee platform. Previous research mainly concentrated on the quality of products offered (Thwe, Tungkasthan & Jongsawat, 2021), the feasibility of this platform as an e-commerce system (Suroso et al, 2020;Erpurini, 2021), and the investigation of customer's perception and behaviour towards this platform (Hidayah & Putri, 2021;Savero & Usman, 2021;Hidayah & Rejeki, 2021). Some exceptions include Km and Tamalanrea (2021) and Sufriadi (2021), whereby they explored fraud threats from the law perspective on buying and selling between buyer and seller via the online platform.…”

Section: Introductionmentioning

confidence: 99%

Early Detection Method for Money Fraudulent Activities on E-commerce Platform via Sentiment Analysis

Misirana

Tan

Saw

et al. 2021

JEB

View full text Add to dashboard Cite

Shopee is one of the prominent online shopping platforms in Malaysia. Nonetheless, countless scam cases were reported on the platform, particularly on money fraudulent activities. This study constructed a quantitative model through linear programming that assessed sentiments based on customers’ reviews. Reviews from three selected Shopee products (‘M3 Smart Health Watch’, ‘Sony Headset Wired Gaming Headphone’, and ‘20000mAh Pineng 100% Original Powerbank’) were analysed using the proposed model. The data were converted into measurable metrics to enable quantitative fraud detection. The model enabled the early detection of possible money fraudulent activities on Shopee products based on customers’ reviews. Resultantly, ‘M3 Smart Health Watch’ is an authentic Shopee product. In contrast, ‘Sony Headset Wired Gaming Headphone’ and ‘20000mAh Pineng 100% Original Powerbank’ are money fraud products sold by scammers. The proposed model utilises free and readily available software, thus extending its usability to other small business owners.

show abstract

Quality Analysis of Shopee Seller Portal by Using Category Recommendation System Approach

Cited by 2 publications

References 9 publications

A Semi-Supervised Learning Approach for Automatic Detection and Fashion Product Category Prediction with Small Training Dataset Using FC-YOLOv4

A Semi-Supervised Learning Approach for Automatic Detection and Fashion Product Category Prediction with Small Training Dataset Using FC-YOLOv4

Early Detection Method for Money Fraudulent Activities on E-commerce Platform via Sentiment Analysis

Contact Info

Product

Resources

About