Databases are the core part of any product, with new companies getting merged and creating cross-functional teams, database merging has become one of the crucial tasks to maintain the efficiency of the product. In the process of database merging, generally, Schemas get redesigned, and Schema Matching is the first step for it. Schema Matching is a method of finding attributes in database fields that are either similar to each other linguistically or represent the same information. Indeed various approaches exist to do automated schema matching, but they fail in different scenarios, such as different language-based fields. In this paper, We explored existing methods (centroid, self-organizing maps, etc.) and proposed a hybrid approach framework that uses both provided data and the schema name to solve a one-to-one schema matching problem. We also introduced the creation of a global dictionary method for one-to-many matching. In global dictionary method, we maps similar fields to same groups using feature extraction and clustering. We have performed experiments using both techniques and compared them to existing approaches. We were able to attain an F1 Score of 0.71 using our hybrid approach, an increase from 0.69 using the existing centroid approach.
Time Series Forecasting has been an active area of research due to its many applications ranging from network usage prediction, resource allocation, anomaly detection, and predictive maintenance. Numerous publications published in the last five years have proposed diverse sets of objective loss functions to address cases such as biased data, long-term forecasting, multicollinear features, etc. In this paper, we have summarized 14 well-known regression loss functions commonly used for time series forecasting and listed out the circumstances where their application can aid in faster and better model convergence. We have also demonstrated how certain categories of loss functions perform well across all data sets and can be considered as a baseline objective function in circumstances where the distribution of the data is unknown. Our code is available at GitHub: https://github.com/aryan-jadon/Regression-Loss-Functions-in-Time-Series-Forecasting-Tensorflow.
Time-series forecasting has been an important research domain for so many years. Its applications include ECG predictions, sales forecasting, weather conditions, even COVID-19 spread predictions. These applications have motivated many researchers to figure out an optimal forecasting approach, but the modeling approach also changes as the application domain changes. This work has focused on reviewing different forecasting approaches for telemetry data predictions collected at data centers. Forecasting of telemetry data is a critical feature of network and data center management products. However, there are multiple options of forecasting approaches that range from a simple linear statistical model to high capacity deep learning architectures. In this paper, we attempted to summarize and evaluate the performance of well known time series forecasting techniques. We hope that this evaluation provides a comprehensive summary to innovate in forecasting approaches for telemetry data.