Cross-Domain Transfer Learning for Demand Forecasting: Using Social Media Sentiment from Related Industries
Sweta Kumari · Journal for Research in Applied Sciences and Biotechnology · 2022
This study examines various window-based techniques, including time-based, size-based, and hybrid approaches, and evaluates their effectiveness in improving extract performance. Through extensive analysis and empirical testing, we demonstrate that window-based strategies can significantly reduce processing time and resource utilization while maintaining data consistency and integrity. This research paper investigates the application of window-based refresh strategies to enhance the performance of data extracts in large-scale data management systems. Traditional extract, transform, load (ETL) processes often struggle with the increasing volume and velocity of data in modern environments. Window-based refresh strategies offer a promising solution by focusing on specific subsets of data during each refresh cycle. This paper shall be devoted to assessing the efficiency of window-based refresh strategies related to the issues described above. The primary research goals are: Propose a general framework with which to apply window-based refresh strategies during the data extract process. Assess the performance benefits derived from applying different types of approaches based on window-based forms as opposed to conventional full and incremental extracts.