• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.97-117
• /
• 2021

Predicting term deposit subscriptions is one of representative financial marketing in banks, and banks can build a prediction model using various customer information. In order to improve the classification accuracy for term deposit subscriptions, many studies have been conducted based on machine learning techniques. However, even if these models can achieve satisfactory performance, utilizing them is not an easy task in the industry when their decision-making process is not adequately explained. To address this issue, this paper proposes an explainable scheme for term deposit subscription forecasting. For this, we first construct several classification models using decision tree-based ensemble learning methods, which yield excellent performance in tabular data, such as random forest, gradient boosting machine (GBM), extreme gradient boosting (XGB), and light gradient boosting machine (LightGBM). We then analyze their classification performance in depth through 10-fold cross-validation. After that, we provide the rationale for interpreting the influence of customer information and the decision-making process by applying Shapley additive explanation (SHAP), an explainable artificial intelligence technique, to the best classification model. To verify the practicality and validity of our scheme, experiments were conducted with the bank marketing dataset provided by Kaggle; we applied the SHAP to the GBM and LightGBM models, respectively, according to different dataset configurations and then performed their analysis and visualization for explainable term deposit subscriptions.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.153-166
• /
• 2021

A main goal of pharmacogenomics studies is to predict individual's drug responsiveness based on high dimensional genetic variables. Due to a large number of variables, feature selection is required in order to reduce the number of variables. The selected features are used to construct a predictive model using machine learning algorithms. In the present study, we applied several hybrid feature selection methods such as combinations of logistic regression, ReliefF, TurF, random forest, and LASSO to a next generation sequencing data set of 400 epilepsy patients. We then applied the selected features to machine learning methods including random forest, gradient boosting, and support vector machine as well as a stacking ensemble method. Our results showed that the stacking model with a hybrid feature selection of random forest and ReliefF performs better than with other combinations of approaches. Based on a 5-fold cross validation partition, the mean test accuracy value of the best model was 0.727 and the mean test AUC value of the best model was 0.761. It also appeared that the stacking models outperform than single machine learning predictive models when using the same selected features.

• Journal of Convergence for Information Technology
• /
• v.12 no.3
• /
• pp.1-10
• /
• 2022

Vegetables such as cabbage are greatly affected by natural disasters, so price fluctuations increase due to disasters such as heavy rain and disease, which affects the farm economy. Various efforts have been made to predict the price of agricultural products to solve this problem, but it is difficult to predict extreme price prediction fluctuations. In this study, cabbage prices were analyzed using the ensemble Voting technique, a method of determining the final prediction results through various classifiers by combining a single classifier. In addition, the results were compared with LSTM, a time series analysis method, and XGBoost and RandomForest, a boosting technique. Daily data was used for price data, and weather information and price index that affect cabbage prices were used. As a result of the study, the RMSE value showing the difference between the actual value and the predicted value is about 236. It is expected that this study can be used to select other time series analysis research models such as predicting agricultural product prices

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.317-317
• /
• 2021

효율적인 물관리를 위한 댐 유입량 대한 연구는 필수적이다. 본 연구에서는 다양한 머신러닝 알고리즘을 통해 40년동안의 기상 및 댐 유입량 데이터를 이용하여 소양강댐 유입량을 예측하였으며, 그 중 고유량과 저유량예측에 적합한 알고리즘을 각각 선정하여 머신러닝 알고리즘을 결합한 CombML을 개발하였다. 의사 결정 트리 (DT), 멀티 레이어 퍼셉트론 (MLP), 랜덤 포레스트(RF), 그래디언트 부스팅 (GB), RNN-LSTM 및 CNN-LSTM 알고리즘이 사용되었으며, 그 중 가장 정확도가 높은 모형과 고유량이 아닌 경우에서 특별히 예측 정확도가 높은 모형을 결합하여 결합 머신러닝 알고리즘 (CombML)을 개발 및 평가하였다. 사용된 알고리즘 중 MLP가 NSE 0.812, RMSE 77.218 m3/s, MAE 29.034 m3/s, R 0.924, R2 0.817로 댐 유입량 예측에서 최상의 결과를 보여주었으며, 댐 유입량이 100 m3/s 이하인 경우 앙상블 모델 (RF, GB) 이 댐 유입 예측에서 MLP보다 더 나은 성능을 보였다. 따라서, 유입량이 100 m3/s 이상 시의 평균 일일 강수량인 16 mm를 기준으로 강수가 16mm 이하인 경우 앙상블 방법 (RF 및 GB)을 사용하고 강수가 16 mm 이상인 경우 MLP를 사용하여 댐 유입을 예측하기 위해 두 가지 복합 머신러닝(CombML) 모델 (RF_MLP 및 GB_MLP)을 개발하였다. 그 결과 RF_MLP에서 NSE 0.857, RMSE 68.417 m3/s, MAE 18.063 m3/s, R 0.927, R2 0.859, GB_MLP의 경우 NSE 0.829, RMSE 73.918 m3/s, MAE 18.093 m3/s, R 0.912, R2 0.831로 CombML이 댐 유입을 가장 정확하게 예측하는 것으로 평가되었다. 본 연구를 통해 하천 유황을 고려한 여러 머신러닝 알고리즘의 결합을 통한 유입량 예측 결과, 알고리즘 결합 시 예측 모형의 정확도가 개선되는 것이 확인되었으며, 이는 추후 효율적인 물관리에 이용될 수 있을 것으로 판단된다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.333-340
• /
• 2023

Efficient prediction of corporate bankruptcy is an important part of making appropriate lending decisions for financial institutions and reducing loan default rates. In many studies, classification models using artificial intelligence technology have been used. In the financial industry, even if the performance of the new predictive models is excellent, it should be accompanied by an intuitive explanation of the basis on which the result was determined. Recently, the US, EU, and South Korea have commonly presented the right to request explanations of algorithms, so transparency in the use of AI in the financial sector must be secured. In this paper, an artificial intelligence-based interpretable classification prediction model was proposed using corporate bankruptcy data that was open to the outside world. First, data preprocessing, 5-fold cross-validation, etc. were performed, and classification performance was compared through optimization of 10 supervised learning classification models such as logistic regression, SVM, XGBoost, and LightGBM. As a result, LightGBM was confirmed as the best performance model, and SHAP, an explainable artificial intelligence technique, was applied to provide a post-explanation of the bankruptcy prediction process.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.3
• /
• pp.215-222
• /
• 2022

The purpose of air traffic flow management is to balance demand and capacity in the national airspace, and its performance relies on an accurate capacity prediction of the airport or airspace. This paper developed a regression model that predicts the number of aircraft actually departing and arriving in a terminal maneuvering area. The regression model is based on a boosting ensemble learning algorithm that learns past aircraft operational data such as time, weather, scheduled demand, and unfulfilled demand at a specific airport in the terminal maneuvering area. The developed model was tested using historical departure and arrival flight data at Incheon International Airport, and the coefficient of determination is greater than 0.95. Also, the capacity of the terminal maneuvering area of interest is implicitly predicted by using the model.

• Journal of Creative Information Culture
• /
• v.7 no.4
• /
• pp.235-242
• /
• 2021

Recently, many human activity recognition(HAR) researches using smartphone sensor data have been studied. HAR can be utilized in various fields, such as life pattern analysis, exercise measurement, and dangerous situation detection. However researches have been focused on recognition of basic human behaviors or efficient battery use. In this paper, exercising activities performed indoors and outdoors were defined and recognized. Data collection and pre-processing is performed to recognize the defined activities by SVM, random forest and gradient boosting model. In addition, the recognition result is determined based on voting class approach for accuracy and stable performance. As a result, the proposed activities were recognized with high accuracy and in particular, similar types of indoor and outdoor exercising activities were correctly classified.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.99-110
• /
• 2023

This study proposed a classification of malicious network traffic using the cyber threat framework(Mitre ATT&CK) and machine learning to solve the real-time traffic detection problems faced by current security monitoring systems. We applied a network traffic dataset called UNSW-NB15 to the Mitre ATT&CK framework to transform the label and generate the final dataset through rare class processing. After learning several boosting-based ensemble models using the generated final dataset, we demonstrated how these ensemble models classify network traffic using various performance metrics. Based on the F-1 score, we showed that XGBoost with no rare class processing is the best in the multi-class traffic environment. We recognized that machine learning ensemble models through Mitre ATT&CK label conversion and oversampling processing have differences over existing studies, but have limitations due to (1) the inability to match perfectly when converting between existing datasets and Mitre ATT&CK labels and (2) the presence of excessive sparse classes. Nevertheless, Catboost with B-SMOTE achieved the classification accuracy of 0.9526, which is expected to be able to automatically detect normal/abnormal network traffic.

• Tunnel and Underground Space
• /
• v.32 no.6
• /
• pp.502-517
• /
• 2022

As the use of TBM increases, research has recently increased to to analyze TBM data with machine learning techniques to predict the exchange cycle of disc cutters, and predict the advance rate of TBM. In this study, a regression prediction of disc cutte wear of slurry shield TBM site was made by combining machine learning based on the machine data and the geotechnical data obtained during the excavation. The data were divided into 7:3 for training and testing the prediction of disc cutter wear, and the hyper-parameters are optimized by cross-validated grid-search over a parameter grid. As a result, gradient boosting based on the ensemble model showed good performance with a determination coefficient of 0.852 and a root-mean-square-error of 3.111 and especially excellent results in fit times along with learning performance. Based on the results, it is judged that the suitability of the prediction model using data including mechanical data and geotechnical information is high. In addition, research is needed to increase the diversity of ground conditions and the amount of disc cutter data.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.321-335
• /
• 2021

Particulate matter (PM10 and PM2.5 with a diameter less than 10 and 2.5 ㎛, respectively) can be absorbed by the human body and adversely affect human health. Although most of the PM monitoring are based on ground-based observations, they are limited to point-based measurement sites, which leads to uncertainty in PM estimation for regions without observation sites. It is possible to overcome their spatial limitation by using satellite data. In this study, we developed machine learning-based retrieval algorithm for ground-level PM10 and PM2.5 concentrations using aerosol parameters from Geostationary Ocean Color Imager (GOCI) satellite and various meteorological parameters from a numerical weather prediction model during January to December of 2019. Gradient Boosted Regression Trees (GBRT) and Light Gradient Boosting Machine (LightGBM) were used to estimate PM concentrations. The model performances were examined for two types of feature sets-all input parameters (Feature set 1) and a subset of input parameters without meteorological and land-cover parameters (Feature set 2). Both models showed higher accuracy (about 10 % higher in R2) by using the Feature set 1 than the Feature set 2. The GBRT model using Feature set 1 was chosen as the final model for further analysis(PM10: R2 = 0.82, nRMSE = 34.9 %, PM2.5: R2 = 0.75, nRMSE = 35.6 %). The spatial distribution of the seasonal and annual-averaged PM concentrations was similar with in-situ observations, except for the northeastern part of China with bright surface reflectance. Their spatial distribution and seasonal changes were well matched with in-situ measurements.