Identification of Actionable Insights from Online Data Sources by using the Hashed Coherence Frequency Calculator (HCFC) Algorithm

Abstract

The present contemporary world is propelled by data. Everyone in society makes decisions based on the existing data and proceeds accordingly. Furthermore, all machinery is automated using advanced technologies such as Artificial Intelligence (AI), Internet of Things (IoT), Machine Learning (ML), and Data Science (DL), which predominantly harness data-driven insights for daily operations. Business organizations, social media, healthcare, big data analytics, and locality mapping are just a few modern industries that rely heavily on data-driven strategies. These areas utilize Cloud Computing (CC) to store the data in the cloud and allow access to data on any device. The primary consideration in data-driven terminology is that not all available data is utilized for decision-making. Hence, before adopting a data-driven process, it is essential to identify a collection of trustworthy and actionable insights that will enable better decision-making. This paper proposes a novel algorithm, the Hashed Coherence Frequency Calculator (HCF), for segregating actionable and non-actionable insights from the given dataset and enabling better decision-making. The algorithm is applied over two case studies containing Amazon product reviews and Google Play Store Apps review datasets.  The coherent frequency count statistical measure is mainly applied to identify actionable insights, and the outcomes will also be compared with the existing approaches.