The effects of data balancing approaches: A case study

Mooijman, P.J.W.; Çatal, Çağatay; Tekinerdoğan, Bedir; Lommen, Arjen; Blokland, Marco

doi:10.1016/j.asoc.2022.109853

Cited by 13 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…SelectKBest evaluates feature relevance using different scoring systems and eliminates all but the k best characteristics (Mooijman et al, 2023).…”

Section: Figure 1 Flowchart Of the Used Methodology Of The Studymentioning

confidence: 99%

Comparative Machine Learning Models for Predicting Loan Fructification in a Semi-Urban Area

Mpia,

Syasimwa,

Muyisa

2024

AAES

View full text Add to dashboard Cite

The current research proposes a reliable and robust machine learning (ML) model which outperforms among six other models in predicting loan fructification obtained by entrepreneurs in a semi-urban area. The proposed model predicts if an entrepreneur can make grow a loan from a microfinance firm, a bank, a financial company, or an individual. The proposed model uses primary data collected from entrepreneurs residing in Butembo, a semi-urban town located in eastern of the democratic republic of Congo as dataset. This study uses a dataset that contains 5868 records. Seven ML model performances are compared in the loan fructification prediction: support vector machine, random forest, extra-trees, decision tree, naïve bayes, k-nearest neighbors, and logistic regression. Support vector machine reveals to be the best model for predicting loan fructification using features such as age, years of working experience of the entrepreneur, entrepreneur loan repayment conviction, used mean by the lender to recover its loan, entrepreneur opinion on the disadvantage of taking out a loan, capacity of the entrepreneur to invest after obtaining loan, entrepreneur position on the possibility of launching a business without a loan, entrepreneur willingness to apply again for loan in the future, success project after obtaining loan. The study uses accuracy, recall, precision, and f-score as metrics to assess the developed models. The four metrics for support vector machine scored 95%, 95%, 83%, and 83%, respectively. The proposed model confirms the robustness of support vector machine in predicting loan fructification.

show abstract

“…SelectKBest evaluates feature relevance using different scoring systems and eliminates all but the k best characteristics (Mooijman et al, 2023).…”

Section: Figure 1 Flowchart Of the Used Methodology Of The Studymentioning

confidence: 99%

Comparative Machine Learning Models for Predicting Loan Fructification in a Semi-Urban Area

Mpia,

Syasimwa,

Muyisa

2024

AAES

View full text Add to dashboard Cite

show abstract

“…Some classical data preprocessing techniques were used in this step like z-normalization [22], log transformation [23], outlier removal [24], one-hot encoding [25], and label encoding [26] to unlock the potential of the predictive models used in this work as shown in Figure 15. Another different technique was used for the time-series approach which may be called LogPlus and was introduced as a trainable layer for the deep learning model.…”

Section: Data Preprocessingmentioning

confidence: 99%

A novel artificial intelligent-based approach for real time prediction of telecom customer’s coming interaction

Hussien,

Mahgoub,

Youssef

et al. 2024

IJEECS

View full text Add to dashboard Cite

<p><span>Predicting customer’s behavior is one of the great challenges and obstacles for business nowadays. Companies take advantage of identifying these future behaviors to optimize business outcomes and create more powerful marketing strategies. This work presents a novel real-time framework that can predict the customer’s next interaction and the time of that interaction (when that interaction takes place). Furthermore, an extensive data exploratory analysis is performed to gain more insights from the data to identify the important features. Transactional data and static profile data are integrated to feed a deep learning model which is implemented using two methodologies: time-series approach and statistical approach. It is found that the time-series approach gives the best performance and fulfills all the requirements. The experiments show that the proposed framework introduces a good overall performance in comparison to existing approaches based on standard metrics like accuracy and mean absolute error (MAE) values. What makes the proposed work novel and special is that it is the first approach that addresses the telecom customer’s next future interaction not just churn prediction like the other approaches in literature.</span></p>

show abstract

“…This study employs the Random Under-sampling (RUS) and Random Oversampling (ROS) techniques as well as a combination of both. Notably, both techniques are known for their high efficacy [26].…”

Section: Imbalanced Datasets Dealingmentioning

confidence: 99%

Optimizing Neural Networks for Academic Performance Classification Using Feature Selection and Resampling Approach

Supriyadi,

Purwanto,

Warsito

2023

mendel

View full text Add to dashboard Cite

The features present in large datasets significantly affect the performance of machine learning models. Redundant and irrelevant features will be rejected and cause a decrease in machine learning model performance. This paper proposes HyFeS-ROS-ANN: Hybrid Feature Selection and Resampling combination method for binary classification using artificial neural network multilayer perceptron (MLP). The first stage of this approach is to use a combination of two feature selection methods to select essential features that are highly correlated with model performance. The second stage of this approach is to use a combination of resampling methods to handle unbalanced data classes. Both approaches are applied to the academic performance classification model using the MLP neural network. This research dataset is obtained using three-dimensional (3D) frameworks such as the Big Five Personality to determine the Personality that affects academic performance from the student dimension, the Family Influence Scale (FIS), which measures factors that affect academic performance from the family dimension, and Higher Education Institutions Service Quality (HEISQUAL) to measure service quality and its influence on academic performance from the Education institution dimension. Previous research shows that the CoR-ANN algorithm has a model accuracy rate of 94%. The research results based on the dataset show that our proposed method can improve accuracy by selecting more relevant and essential features in improving model performance. The results show that the features are reduced from 135 to 108, while the HyFS-ROS-ANN model for binary classification accuracy increases to 100%.

show abstract

The effects of data balancing approaches: A case study

Cited by 13 publications

References 20 publications

Comparative Machine Learning Models for Predicting Loan Fructification in a Semi-Urban Area

Comparative Machine Learning Models for Predicting Loan Fructification in a Semi-Urban Area

A novel artificial intelligent-based approach for real time prediction of telecom customer’s coming interaction

Optimizing Neural Networks for Academic Performance Classification Using Feature Selection and Resampling Approach

Contact Info

Product

Resources

About