Utilising Sampling Methods to Improve the Prediction on Customers’ Buying Intention

Yap, Chau-Tean; Khor, Kok-Chin

doi:10.1109/dasa54658.2022.9765293

Cited by 2 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, a two-class dataset is often considered imbalanced (or skewed) when the minority class is significantly underrepresented in contrast to the dominant class. In machine learning and data mining, imbalanced datasets are a constant worry because they make it difficult for machine learning algorithms to learn minority classes efficiently [25]. Hence, the researcher should consider balancing the two-class data with trained data to avoid misrepresenting the minority class.…”

Section: Sampling For Imbalanced Datasetmentioning

confidence: 99%

“…Another resampling method that previous researchers have widely used is Randomly Under-Sampling (RUS), which reduces the frequency of the majority class in the training set [28]. However, too much data removal may result in the prediction model training with inadequate data and poor performance [25,27]. However, [29] suggested that the effectiveness of balancing techniques varies widely depending on the classifier and feature set being used, and not all balancing strategies operate similarly.…”

Section: Sampling For Imbalanced Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Life Insurance Prediction and Its Sustainability Using Machine Learning Approach

2023

View full text Add to dashboard Cite

Owning life insurance coverage that is not enough to pay for the expenses is called underinsurance, and it has been found to have a significant influence on the sustainability and financial health of families. However, insurance companies need to have a good profile of potential policyholders. Customer profiling has become one of the essential marketing strategies for any sustainable business, such as the insurance market, to identify potential life insurance purchasers. One well-known method of carrying out customer profiling and segmenting is machine learning. Hence, this study aims to provide a helpful framework for predicting potential life insurance policyholders using a data mining approach with different sampling methods and to lead to a transition to sustainable life insurance industry development. Various samplings, such as the Synthetic Minority Over-sampling Technique, Randomly Under-Sampling, and ensemble (bagging and boosting) techniques, are proposed to handle the imbalanced dataset. The result reveals that the decision tree is the best performer according to ROC and, according to balanced accuracy, F1 score, and GM comparison, Naïve Bayes seems to be the best performer. It is also found that ensemble models do not guarantee high performance in this imbalanced dataset. However, the ensembled and sampling method plays a significant role in overcoming the imbalanced problem.

show abstract

Section: Sampling For Imbalanced Datasetmentioning

confidence: 99%

Section: Sampling For Imbalanced Datasetmentioning

confidence: 99%

Life Insurance Prediction and Its Sustainability Using Machine Learning Approach

2023

View full text Add to dashboard Cite

show abstract

“…Under the background of the steady increase of online sales, there is a huge untapped market potential for online shopping [2]. One of the challenges facing e-commerce is to predict the purchasing power of customers so that businesses more reasonable purchases [3]. Researchers use machine learning techniques to study such problems.…”

Section: Introductionmentioning

confidence: 99%

Analysis of buying intension online based on decision tree and support vector machine

Zhang

2024

ACE

View full text Add to dashboard Cite

With the development of the Internet, online shopping has gradually emerged and changed people's living habits. On this basis, the purchase intention of users has become a hot topic. In this study, the data set on Kaggle is used to train and analyse the model with decision tree as well as support vector machine (SVM). To be specific, 30% of the data is used for testing. According to the feature correlation analysis, one can see that some features, such as ExitRates and BounceRates, are highly correlated, and PageValue has a great impact on income. In addition, precision, recall, f1-score and other data were processed to evaluate the model, and its limitations and future development were explained. It is of great significance to forecast the income of online merchants and how merchants purchase goods and reduce inventory, and to understand and predict the intention of users to purchase online from the income of merchants.

show abstract

Utilising Sampling Methods to Improve the Prediction on Customers’ Buying Intention

Cited by 2 publications

References 15 publications

Life Insurance Prediction and Its Sustainability Using Machine Learning Approach

Life Insurance Prediction and Its Sustainability Using Machine Learning Approach

Analysis of buying intension online based on decision tree and support vector machine

Contact Info

Product

Resources

About