Search results

Introduction: Lending is an age-old concept, and Peer-to-Peer (P2P) lending is not new. The reduction in the issuing of loans by banks has made people switch from traditional to online mode. The introduction of the online P2P lending industry is in its nascent stage of growth. As this industry is relatively new, understanding user experience, sentiments, and emotions would be helpful for the industry to innovate as per customer requirements.

Purpose: To explore the patterns in the sentiments expressed by users of ‘Cashkumar’ based on Google reviews.

Methodology: Sentiments have been analysed using user experience in risk, cost, ease of use, and loan processing time. Python application was used for sentiment analysis of Google reviews.

Findings: The sentiment analysis results showed that the average sentiment score was 0.7144, which indicates that the user sentiment towards ‘Cashkumar’ is positive. The reviews reflect that the users, especially borrowers were satisfied with the platform’s services and happy with loan processing time. The other factors – ease of use, cost, and risk – were not given much importance by users. Both lenders and borrowers faced a few issues, but the results of the lender’s sentiment analysis could not be generalised due to a smaller number of posted reviews.

Need: The previous suggestion assists with administrative methodology. The contribution explores customer understandings in different industry and transaction texts. They include online education, video marketing, and entertainment analytics. The communication needs to be detailed to improve the system.

Purpose: The suggestion aims to improve the previous contribution by enhancing the user experience. The study increases the usage of video content. The recommendation brings better business to the video host.

Methodology: The work includes the machine learning algorithm to understand the user and improve the client’s experience. The recommendation uses the Apriori algorithm to map various attributes of the trainer and learners. The suggested work has three features. It focusses on video possessions, educator feelings, physical characteristics, and visible aesthetic characteristics. The study considers 1,200 different samples.

Findings: The work simulates using python. It improves efficiency by 29.5% compared to previous work.

Practical Implications: Machine learning has pitched in to understand diverse customers’ behaviour. Various features affecting the behaviour are collected and analysed by the system. The study intends to find an appropriate mapping between the attributes of the user and educator.