Cancer is the leading disease in the world by the increasing number of new patients and deaths every year. Hence, it is the most feared disease of our time. It is believed that lung cancer and breast cancer are most common types of cancer and they both are subtypes of the same group of cancer – carcinoma. With this type of cancer early detection is of great importance for patient survival. As it is the disease that has unfortunately been around for many years, today we have datasets with all necessary information for diagnosing and predicting cancer. Predicting cancer means deciding if the cancer is malignant or benign. The key to this answer lays in different values of parameters that have been stored when the disease was discovered. Machine learning plays the crucial role in predicting cancer, given the fact that algorithms such as Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF) and etc. are designed to find the pattern that occurs in large sets of data and based on that make a decision. In this paper, author's goal is to see how machine learning and its practical implementation on public datasets can help with early breast cancer diagnosis and hopefully help save more lives.
The purpose of the credit scoring process is the classification of the loan as default or non-default trying to reduce the risk for financial institutions. Paper aims to illustrate the implementation of a credit scoring model using boosting techniques. Specifically, the proposed solution is implemented using XGBoost algorithm discussing the role of hyperparameter tuning and feature selection in result optimization. Data used for obtaining performance scores is real-world data provided by a microfinance institution based in Bosnia and Herzegovina. Results suggest that significant optimization of XGBoost may be performed, yet, the model fails to outperform typically recommended approaches for solving credit scoring problem. Given that, it is suggested that although boosting techniques are increasingly being relied upon, it is unaccountable to make a decision without understanding the specificity of data and questioning whether other techniques are more suitable.
The problem of nonperforming loans is one of the biggest problems in the banking sector. In order to mitigate this problem, it is necessary to improve the methods of credit risk assessment. One way to minimize credit risk is to improve the assessment of the creditworthiness of the applicant. In order to make a more accurate assessment, many models have been developed using classification techniques. This paper demonstrates the use of classification techniques in the form of a single classifier or in a classifier ensemble setting. We proposed bagging as a model ensemble using artificial neural networks. In the experiment conducted with the Bosnian commercial banks dataset, the proposed model showed promising results according to evaluation criteria, especially after the process of feature selection. Both individual and wrapper feature selection methods were used. Bagging with neural network (NNBag) outperforms commonly used techniques with accuracy improvement from 1% to 5%. The superiority of the proposed model (NNBag) is confirmed on two widely available datasets for assessing creditworthiness. Based on experimental results on three datasets, it is proven that NNBag is suitable for use in the assessment of the creditworthiness of applicants.
Nema pronađenih rezultata, molimo da izmjenite uslove pretrage i pokušate ponovo!
Ova stranica koristi kolačiće da bi vam pružila najbolje iskustvo
Saznaj više