Treffer: DEVELOPMENT OF TRANSFORMATION OF LECTURER PERFORMANCE THROUGH PRO GROWTH CONSTRUCTIVE INTERACTION WITH A MULTIDIMENSIONAL APPROACH AND MACHINE LEARNING BASED MATHEMATICAL MODELS.

The object of this research is to focus on the Pro Growth Constructive Interaction (PGCI) approach as a strategy to improve lecturer performance. PGCI integrates multidimensional interactions involving academic, social, technological, individual, external and temporal dimensions to achieve optimal productivity and efficiency. In this research, there is a main problem to be addressed, namely identifying and optimizing the factors that influence lecturer performance by developing a comprehensive model that is able to predict and improve performance through multidimensional interactions. The research results obtained were the dimension contribution showing the highest contribution to lecturer performance (0.177062), followed by the technological (0.174122), social (0.167044), external (0.165670), and individual (0.163610) dimensions). In the results of the mathematical model with the Lagrangian method optimized with a machine learning algorithm distributing weights with a focus on external dimensions (0.2650) and technology (0.2179), resulting in a performance increase of 7.35 %. This model is able to achieve an accuracy of 92.4 % in predicting lecturer performance using a deep neural network algorithm. In this research, there is a brief interpretation of the research findings showing that the temporal and technological dimensions have an important role in determining lecturer performance. By prioritizing these two dimensions, the optimized model yields significant improvements. Characteristics obtained from research, multidimensional analysis covering various aspects of performance and high accuracy and measurable performance improvements prove the reliability of the model. The results of this research have significant practical applications in higher education institutions [ABSTRACT FROM AUTHOR]

Copyright of Eastern-European Journal of Enterprise Technologies is the property of PC TECHNOLOGY CENTER and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)