دانلود رایگان مقاله شبکه عصبی مصنوعی (ANN) با استفاده از برنامه های کاربردی برای تشخیص تقلب و بازاریابی مستقیم

abstract

The rapid growth in data capture and computational power has led to an increasing focus on data-driven research. So far, most of the research is focused on predictive modeling using statistical optimization, while profit maximization has been given less priority. It is exactly this gap that will be addressed in this study by taking a profit-driven approach to develop a profit-driven Artificial Neural Network (ANN) classification technique. In order to do this, we have first introduced an ANN model with a new penalty function which gives variable penalties to the misclassification of instances considering their individual importance (profit of correctly classification and/or cost of misclassification) and then we have considered maximizing the total net profit. In order to generate individual penalties, we have modified the sum of squared errors (SSE) function by changing its values with respect to profit of each instance. We have implemented different versions of ANN of which five of them are new ones contributed in this study and two benchmarks from relevant literature. We appraise the effectiveness of the proposed models on two real-life data sets from fraud detection and a University of California Irvine (UCI) repository data set about bank direct marketing. For the comparison, we have considered both statistical and profit-driven performance metrics. Empirical results revealed that, although in most cases the statistical performance of new models are not better than previous ones, they turn out to be better when profit is the concern.

5. Summary and conclusion

In this study, a novel profit-based neural network has been proposed which makes the classification considering all individual costs and profits of each of the instances and consequently maximizes the total net profit captured from applying the classification model. For this purpose, we modified the neural network error function which is sensitive to each instance's misclassification considering its profitability. Different models have been proposed to generate weights (penalties) for modification of error function. All of the models, class-based cost-sensitive ANN (CNN) and two well-known classifiers, Decision tree and Naïve Bayes, have been tested on two real-life fraud data sets and a UCI direct marketing data set. In order to evaluate the classifiers, both accuracy-based and profit-based performance metrics have been used.