Performance Analysis of Different Machine Learning in Customer Prediction

Abstract

Performing effective consumer analysis allows businesses to gain a better understanding of their customers' relationships with them and how satisfied they are with the products or services they provide. Moreover, identifying unp otential customers within an enterprise's business aids in the development of adequate business initiatives to enhance customer engagement. Further depending on the customer study report aid to enhance the business process, marketing strategies, and customer retention & satisfaction. To conduct efficient customer analysis, in this work machine learning algorithms are applied. ML algorithms are classified into three types: one is supervised learning, the second is unsupervised learning and the last one is reinforcement learning. In this work, three different supervised learning models are applied to perform efficient customer analysis. This research uses LR, K-NN, and NB models to perform customer analysis. The study was executed with the customer data that was captured from UCI repository. Further experimental findings obtained from three different models are captured and indicated using different parameters like accuracy, sensitivity, sp ecificity, TP Rate, FP Rate, and Precision. The exp erimental results show NB model archives better performance in customer analysis compared to LR andK-NN.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 20 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.