No abstract

The human disease prediction is specifically a struggling piece of work for an accurate and on time treatment. Around the world, diabetes is a hazardous disease. It affects the various essential organs of the human body, for example, nerves, retinas, and eventually heart. By using models of machine learning algorithms, we can recommend and predict diabetes on various healthcare datasets more accurately with the assistance of an intelligent healthcare recommendation system. Not long ago, for the prediction of diabetes, numerous models and methods of machine learning have been introduced. But despite that, enormous multi-featured healthcare datasets cannot be handled by those systems appropriately. By using Machine Learning, an intelligent healthcare recommendation system is introduced for the prediction of diabetes. Ultimately, the model of machine learning is trained to predict this disease along with K-Fold Cross validation testing.  The evaluation of this intelligent and smart recommendation system is depending on datasets of diabetes and its execution is differentiated from the latest development of previous literatures. Our system accomplished 99.0% of efficiency with the shortest time of 12 Milliseconds, which is highly analyzed by the previous existing models of machine learning. Consequently, this recommendation system is superior for the prediction of diabetes than the previous ones. This system enhances the performance of automatic diagnosis of this disease. Code is available at (https://github.com/RaoHassanKaleem/Diebetes-Detection-using-Machine-Learning-Algorithms).

Customers' needs drive the competitive nature of today's business environment. To achieve desired outcomes, resources must be transformed effectively and efficiently. Performance evaluation is one of the most important benchmarking tools for modern businesses due to sophisticated technologies, computerized processes, communication, and fierce competition. The study analyzed the performance of 26 commercial banks from 2008 to 2016. Efficiency and effectiveness were calculated using data envelopment analysis(DEA). The results showed that the sub-optimal performance of banks was caused mainly by ineffectiveness compared to Efficiency. Banks were further categorized into four groups based on their average efficiency and effectiveness scores into Ace, Underdogs, Lucky, and Unlucky. This matrix suggests that banks in the Lucky quadrant should improve Efficiency, those in the Unluck group should diversify, and those in the Underdogs quadrant should merge. Banks in the Lucky, Unlucky, and Underdog quadrants should emulate the Ace quadrant's success.

No abstract