Cost Sensitive Evaluation Measures for F-term Patent Classification
نویسندگان
چکیده
Some classification problems, such as the NTCIR06 F-term patent classification task, have general or specific relations between the target class labels. Consequently, in such cases, it is desirable that the relations among the labels can be taken into account in the evaluation measures. For example, if a system assigns an incorrect label to one instance and the assigned label has close relation with the true label, then the system may deserve some credit, rather than being given no credit at all as is the case with conventional evalu-
منابع مشابه
Ensemble Classification and Extended Feature Selection for Credit Card Fraud Detection
Due to the rise of technology, the possibility of fraud in different areas such as banking has been increased. Credit card fraud is a crucial problem in banking and its danger is over increasing. This paper proposes an advanced data mining method, considering both feature selection and decision cost for accuracy enhancement of credit card fraud detection. After selecting the best and most effec...
متن کاملSVM Based Learning System for F-term Patent Classification
This paper describes our SVM-based system and the techniques we used to adapt the approach for the specifics of the F-term patent classification subtask at NTCIR-6 Patent Retrieval Task. Our system obtained the best results according to two of the three measures used for performance evaluation. Moreover, the results from some additional experiments demonstrate that our system has benefited from...
متن کاملNew Evaluation Measures for F-term Patent Classification
Some classification problems, such as the NTCIR06 F-term patent classification task, have general or specific relations between the target class labels. Consequently, in such cases, it is desirable that the relations among the labels can be taken into account in the evaluation measures. For example, if a system assigns an incorrect label to one instance and the assigned label has close relation...
متن کاملA New Formulation for Cost-Sensitive Two Group Support Vector Machine with Multiple Error Rate
Support vector machine (SVM) is a popular classification technique which classifies data using a max-margin separator hyperplane. The normal vector and bias of the mentioned hyperplane is determined by solving a quadratic model implies that SVM training confronts by an optimization problem. Among of the extensions of SVM, cost-sensitive scheme refers to a model with multiple costs which conside...
متن کاملOverview of Classification Subtask at NTCIR-5 Patent Retrieval Task
This paper describes Classification Subtask at NTCIR-5 Patent Retrieval Task. We perform two subtasks for patent classification using a multi-dimensional classification structure called “F-term (File Forming Term) classification system”. The first one is Theme Categorization Subtask, where each participant classifies a patent into technological fields called themes. The second one is F-term Cat...
متن کامل