Evaluation Metrics in Classification: A Quantification of Distance-Bias
نویسندگان
چکیده
This paper provides a characterization of bias for evaluation metrics in classification (e.g., Information Gain, Gini, χ, etc.). Our characterization provides a uniform representation for all traditional evaluation metrics. Such representation leads naturally to a measure for the distance between the bias of two evaluation metrics. We give a practical value to our measure by observing the distance between the bias of two evaluation metrics and its correlation with differences in predictive accuracy when we compare two versions of the same learning algorithm that differ in the evaluation metric only. Experiments on real-world domains show how the expectations on accuracy differences generated by the distance-bias measure correlate with actual differences when the learning algorithm is simple (e.g., search for the best single-feature or the best single-rule). The correlation, however, weakens with more complex algorithms (e.g., learning decision trees). Our results show how interaction among learning components is a key factor to understand learning performance.
منابع مشابه
Evaluation Metrics in Classiication: a Quantiication of Distance-bias
This paper provides a characterization of bias for evaluation metrics in classiica-tion (e.g., Information Gain, Gini, 2 , etc.). Our characterization provides a uniform representation for all traditional evaluation metrics. Such representation leads naturally to a measure for the distance between the bias of two evaluation metrics. We give a practical value to our measure by observing if the d...
متن کاملA Quantiication of Distance-bias between Evaluation Metrics in Classiication
This paper provides a characterization of bias for evaluation metrics in classiication (e.g., Information Gain, Gini, 2 , etc.). Our characterization provides a uniform representation for all traditional evaluation metrics. Such representation leads naturally to a measure for the distance between the bias of two evaluation metrics. We give a practical value to our measure by observing if the di...
متن کاملReview of ranked-based and unranked-based metrics for determining the effectiveness of search engines
Purpose: Traditionally, there have many metrics for evaluating the search engine, nevertheless various researchers’ proposed new metrics in recent years. Aware of this new metrics is essential to conduct research on evaluation of the search engine field. So, the purpose of this study was to provide an analysis of important and new metrics for evaluating the search engines. Methodology: This is ...
متن کاملClassification of LEED World Standard Indicators in Sustainable Architecture of Contemporary Iranian Cities Based on Regional Ecological Characteristics: A Case Study of Qom City
Following developments in urban contexts of contemporary Iran, the creation of new urban contexts and cities has a direct impact on the ecosystem of its surrounding area. Urban neighborhoods on the path to achieving the goal of sustainable urban development require the integration of architecture and the principles of environmental sustainability. Using the Sustainable Architecture approach bas...
متن کاملA comparative study of quantitative mapping methods for bias correction of ERA5 reanalysis precipitation data
This study evaluates the ability of different quantitative mapping (QM) methods as a bias correction technique for ERA5 reanalysis precipitation data. Climate type and geographical location can affect the performance of the bias correction method due to differences in precipitation characteristics. For this purpose, ERA5 reanalysis precipitation data for the years 1989-2019 for 10 selected syno...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Computational Intelligence
دوره 19 شماره
صفحات -
تاریخ انتشار 2003