Data Pre-Processing Algorithm for Neural Network Binary Classification Model in Bank Tele-Marketing

Abstract

Tele-marketing presents a huge challenge in identifying potential customers with lack of effective marketing strategy may led a company to succumbs to problems such as prolonged marketing campaign. Various attempts to improve the performance of binary classification model for bank tele-marketing data. Previous researches indicate that the neural network is the most common algorithms being employed and able to produce commendable results with higher accuracy percentages compared to other algorithms. Despite several attempts to improve the model through treatment of imbalance dataset and features selection, this research argues that they are incomplete. Therefore, this research proposes a data pre-processing algorithm for bank tele-marketing binary classification neural network. Three datasets have been employed (19, 16, and 20 features) to evaluate the performance of the algorithm towards the classification model. The data pre-processing algorithm is divided into three phases; data cleaning, data imbalance treatment and finally data normalization. In this paper, the result indicated that binary classification model complemented with data cleaning techniques such as Missing common (MC) and Tomek Links (TL) shows a better result compared to Ignore Missing (IM). In terms of data normalization, techniques such as MaxAbsScaler (MAS) and MinMaxScaler (MMS) consistently indicated better performance from other normalization techniques. The classification model employed in this paper utilize data pre-processing algorithm combination of MC-TL-MMS. The algorithm using this approach able to record an area of the receiver operating characteristic curve (AUC) of 0.9129 and 0.9464 by using 16 features and 20 features respectively. This result presents the highest figure in terms of performance accuracy compared to other previous researches

Machine Learning Approach and Model Performance Evaluation for Tele-Marketing Success Classification

“…According to the true positive rate, the best result was obtained by Logistic Regression. In the study of Halim et al (2020), a model has been developed to predict successful calls with the telemarketing data set. In the model, especially the data pre-processing phase has been emphasized, the data set has been passed through various data cleaning, balancing and normalization processes.…”

Teknik Random Undersampling untuk Mengatasi Ketidakseimbangan Kelas pada CT Scan Kista Ginjal

“…CNN perlu dilatih menggunakan data pelatihan dan pengujian sehingga dapat menghasilkan hasil yang akurat. Selain itu, penggunaan teknik pre-processing pada data yang dapat meningkatkan performa modeling dengan cara memperbanyak variasi data gambar, sehingga model klasifikasi dapat lebih efektif [6]. Dalam membuat model klasifikasi perlu memperhatikan pemahaman data, tingkat interpretabilitas model, dan penanganan overfitting.…”

Non-Intrusive Load Classification and Recognition Using Soft-Voting Ensemble Learning Algorithm With Decision Tree, K-Nearest Neighbor Algorithm and Multilayer Perceptron

“…Data normalization in machine-learning algorithms offers two advantages: improving model convergence and enhancing accuracy. Several methods have been used for data normalization, including min-max normalization, MaxAbs scaler, robust scaler, z-score normalization, L1 normalization, and the Yeo-Johnson transformation [21][22][23].…”