Combining Domain Knowledge & Machine Learning

Abstract

The latest hit on technology is the information and telecommunication novelties. Internet and big data are important source of information in order to understand this vast majority of the upcoming knowledge. Websites are progressively expanding and making it available to everyone who has access. Modern economic systems are built on data or knowledge. Thus, tech companies gather huge data and exercise their powers to digitalize the information to capture and utilize the knowledge within their reach. Information management enables firms to improve customer satisfaction, increase revenue, understand customer behavior, mitigate risk assessment, making a multidisciplinary approach. Another approach is to be able to identify business strategies. Information management researches (using machine learning algorithm) can help the field to discover what is significant on a customer behavior and reduce costs to its clients. Over the recent years, information management and machine learning algorithms are getting more and more close and on topic. Since, information management and machine learning intensely concerns with domain knowledge. Artificial Intelligence allows the machines to accumulate knowledge and adapts it. Information management and machine learning are affected by several factors such as business strategies, customer behavior, effectively using knowledge. Therefore, pulling only a single topic will not be enough to capture meaningful information from a huge chunk. Machine learning, and information systems also have the potential to help organizations in financial aspects. XG-Boost is one of the algorithms under the Decision-Trees equipped with boosting techniques similar to Microsoft's Light GBM algorithm. In recent years, XG-Boost algorithm has gained huge popularity due to its easy to use, speed, and performance. The aim of this paper is to show the use of the data in order to predict house prices XG-Boost algorithm and Neural Network model. The main goal here is to estimate the house prices using domain knowledge and machine learning algorithms. RMSE criteria was preferred. This paper suggests a generic way to gather knowledge on a very specific domain. Following the achieved result, the house price was estimated by processing the domain info through the machine learning algorithm here presented.