Classification is a significant technique for data mining with wide applications to identify the different categories of data used in virtually every area in our lives. Classification is used to label the individual in relation to the predefined groups according to the characteristics of the individual. This paper sheds light on performance appraisal based on (precision, Recall, F-measure) data classification analysis using a classification algorithm (LogitBoost and Naïve Bay). The Naïve Bayes, algorithm, is based on probability and the LogitBoost algorithm is based on the finding that Adaboost basically matches the training data using an additive logistic regression model. The paper sets out, to render comparative analyses of Naive Bayes and LogitBoost classifiers in the context of job classification dataset, Experimental results revealed that LogitBoost has highest result in (precision = 82.73 percent, recall = 83.33 percent, F-measure = 82.31 percent) compared to the Naive bayes algorithm for the data set mentioned above.