Bank predictions for prospective long-term deposit investors using machine learning LightGBM and SMOTE

Muslim, Much Aziz; Dasril, Yosza; Alamsyah, A; Mustaqim, Tanzilal

doi:10.1088/1742-6596/1918/4/042143

Cited by 5 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Serta belum adanya penelitian yang mengangkat optimalisasi ataupun improvisasi model prediksi menggunakan suatu teknik seperti salah satu contohnya adalah SMOTE (Synthetic Minority Over-sampling Technique). Padahal sebuah studi menunjukkan teknik SMOTE meningkatkan kinerja model terutama untuk kasus dataset yang tidak seimbang [14].…”

Section: Pendahuluanunclassified

Optimalisasi Model Klasifikasi Sentimen Netizen Terhadap Merek Tas Luar Negeri

et al. 2023

View full text Add to dashboard Cite

Abstract Research on text mining has grown more than ever in various sectors. Public figures have also grown in interest towards the field and have the tendency to get to know more about consumers’ perceptions toward relevant goods and the reputation of an individual in social media. Sentiment analysis is a state-of-the-art technique that can be utilized to evaluate such trends or general views, for instance the reputation of a fashion brand. The dataset is built upon the crawled tweets that are relevant with the required topics which have the purpose to analyze the preferred fashion brand of the public. This study shows that the public leads to a positive notion toward foreign bag brands. The algorithms that are being compared includes Logistic Regression, Multinomial Naïve Bayes, Decision Tree, K-Nearest Neighbors, Random Forest, and Support Vector Machine. Support Vector Machine provides the best model which reaches 69% in accuracy. The Synthetic Minority Oversampling Technique (SMOTE) was also conducted to improve the model. Result shows that the Support Vector Machine model has successfully increased its accuracy by 13%, reaching an accuracy of 82%. Keywords: Sentiment Analysis, Brand, Machine Learning, Classification, SMOTE Abstrak Penelitian mengenai text mining telah mengalami peningkatan dibanding sebelumnya di dalam berbagai sektor. Figur publik juga semakin tertarik terhadap bidang tersebut dan memiliki kecenderungan untuk mengetahui lebih banyak mengenai persepsi konsumen terhadap suatu barang dan mengenai reputasi seseorang di media sosial. Sentimen analisis merupakan sebuah teknik state-of-the-art yang dapat digunakan untuk mengevaluasi suatu tren atau pandangan umum mengenai suatu hal, misalnya reputasi sebuah merek fashion. Sumber himpunan data yang digunakan pada penelitian ini dibuat berdasarkan crawling tweet yang relevan dengan topik yang dibutuhkan, yang bertujuan untuk menganalisis merek fashion yang disukai oleh masyarakat. Penelitian ini menunjukkan bahwa persepsi masyarakat mengarah pada persepsi positif terhadap merek tas luar negeri. Pada penelitian ini, beberapa algoritma digunakan sebagai perbandingan, antara lain Logistic Regression, Multinomial Naïve Bayes, Decision Tree, K-Nearest Neighbors, Random Forest, dan Support Vector Machine. Hasil pengujian model menunjukkan algoritma Support Vector Machine memiliki performa terbaik dengan accuracy sebesar 69%. Kemudian digunakan teknik Synthetic Minority Oversampling Technique (SMOTE) untuk meningkatkan performa dari model. Hasil menunjukkan bahwa model algoritma Support Vector Machine telah berhasil ditingkatkan dengan accuracy sebesar 13%, mencapai accuracy sebesar 82%. Kata kunci: Sentimen Analisis, Merek, Pembelajaran Mesin, Klasifikasi, SMOTE

show abstract

Section: Pendahuluanunclassified

Optimalisasi Model Klasifikasi Sentimen Netizen Terhadap Merek Tas Luar Negeri

et al. 2023

View full text Add to dashboard Cite

show abstract

“…A few studies have dealt with customer deposits prediction, and Pangrahi and Patnaik (2020) tried to forecast customer behavior from a bank direct marketing survey using neural network techniques. Muslim et al (2020) in their proposed study applied logistic regression, random forest and light GBM to predict long-term deposit possibilities. Patway et al (2021) used three classification techniques, which are the Naı €ve Bayes, ANN and support vector machine.…”

Section: Literature Reviewmentioning

confidence: 99%

Predicting customer deposits with machine learning algorithms: evidence from Tunisia

Gafrej

2023

View full text Add to dashboard Cite

PurposeThis paper aims to evaluate the performance of the multiple linear regression (MLR) using a fixed-effects model (FE) and artificial neural network (ANN) models to predict the level of customer deposits on a sample of Tunisian commercial banks.Design/methodology/approachTraining and testing datasets are developed to evaluate the level of customer deposits of 15 Tunisian commercial banks over the 2002–2021 period. This study uses two predictive modeling techniques: the MLR using a FE model and ANN. In addition, it uses the mean absolute error (MAE), R-squared and mean square error (MSE) as performance metrics.FindingsThe results prove that both methods have a high ability in predicting customer deposits of 15 Tunisian banks. However, the ANN method has a slightly higher performance compared to the MLR method by considering the MAE, R-squared and MSE.Practical implicationsThe findings of this paper will be very significant for banks to use additional management support to forecast the level of their customers' deposits. It will be also beneficial for investors to have knowledge about the capacity of banks to attract deposits.Originality/valueThis paper contributes to the existing literature on the application of machine learning in the banking industry. To the author's knowledge, this is the first study that predicts the level of customer deposits using banking specific and macroeconomic variables.

show abstract

“…Predicting corporate bankruptcy requires detection stages from bankruptcy datasets [7]. The detected bankruptcy dataset will provide information to improve the accuracy of the results.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Model Using Extreme Gradient Boosting (XGBoost) Feature Importance and Light Gradient Boosting Machine (LightGBM) to Improve Accurate Prediction of Bankruptcy

Syafei,

Efrilianda

2023

Recursive J. of Informatics

View full text Add to dashboard Cite

Abstract. Humans have limitations in processing and analyzing large amounts of data in a short time, including in terms of analyzing bankruptcy data. Bankruptcy data is one of the data that has complex information, so it requires technology that can assist in the process of analyzing and processing data more quickly and efficiently. Data science technology enables data processing and analysis on a large scale, using parallel processing techniques. Parallel processing can be implemented in machine learning models. Purpose: Using parallel processing techniques, data science technologies enable data processing and analysis at scale. Parallel processing can be implemented in machine learning models. Therefore, this study aims to implement a machine learning model using the Light Gradient Boosting Machine (LightGBM) classification algorithm which is optimized using Extreme Gradient Boosting (XGBoost) Feature Importance to increase the accuracy of bankruptcy prediction. Methods/Study design/approach: Bankruptcy prediction is carried out by applying LightGBM as a classification model and optimized using the XGBoost algorithm as a Feature Importance technique to improve model accuracy. the dataset used is the Taiwanese Bankruptcy dataset collected from the Taiwan Economic Journal for 1999 to 2009 and has 6,819 data. Taiwanese Bankruptcy is unbalanced data, so this study applies random oversampling. Result/Findings: The results obtained after going through the model testing process using the confusion matrix obtained an accuracy of the performance of LightGBM+XGBoost Feature Importance of 99.227%. Novelty/Originality/Value: So it can be concluded that the implementation of XGBoost Feature Importance can be used to improve LightGBM's performance in bankruptcy prediction.

show abstract

Bank predictions for prospective long-term deposit investors using machine learning LightGBM and SMOTE

Cited by 5 publications

References 8 publications

Optimalisasi Model Klasifikasi Sentimen Netizen Terhadap Merek Tas Luar Negeri

Optimalisasi Model Klasifikasi Sentimen Netizen Terhadap Merek Tas Luar Negeri

Predicting customer deposits with machine learning algorithms: evidence from Tunisia

Machine Learning Model Using Extreme Gradient Boosting (XGBoost) Feature Importance and Light Gradient Boosting Machine (LightGBM) to Improve Accurate Prediction of Bankruptcy

Contact Info

Product

Resources

About