In steep growth in the consumption of Internet, Big Data came into picture for handling enormous amount of data. However, the data that is generated through internet has high dimensional data. So, feature engineering will be performed—to extract the best feature subset from high dimensional data. Assets are the ones to keep, expand upon, and support for the one who and what is to come. Asset mapping is a positive and charming way to learn about the community. It empowers us to contemplate where individuals live and work. It also challenges us to recognize how other people see the same community. In this paper, a model is introduced to find the required assets based on the population in the area and whether the available assets are tangible are not, is identified by extracting the features from the data gathered from the government of Andhra Pradesh. The data is pre-processed by extracting the best features in it by using feature engineering methods and classifiers like XGBoost, Random Forest and ExtraTreeClassifier. The experimental results proves that XGBoost provides the most accurate results for the specified target.
CITATION STYLE
Sree Divya, K., Bhargavi, P., & Jyothi, S. (2020). XGBoost Classifier to Extract Asset Mapping Features. In Learning and Analytics in Intelligent Systems (Vol. 15, pp. 195–208). Springer Nature. https://doi.org/10.1007/978-3-030-46939-9_18
Mendeley helps you to discover research relevant for your work.