ACADEMIC PERFORMANCE PREDICTION APPLICATION (APPA)

The research study offers a thorough description of the process of deployment after training and testing of the classification model respectively. The performance of students is a crucial prerequisite to help students that don’t perform well in the examination and can impact the final semester result. To overcome the difficulties they come across while learning and assist them to achieve the best results. The researcher uses the advantages of the React-Native platform to build an "APPA" mobile application capable of delivering student performance prediction-related solutions. It also provides a proposed model of student academic success prediction. The further study highlights the further scope of the mobile App built for predicting student performance.

Movie Success Prediction Using Data Mining

The movie industry is arguably one of the biggest entertainment sectors. Nollywood, the Nigerian movie industry produces tons of movies for public consumption, but only a few make it to box-office or end up becoming blockbusters. The introduction of movie success prediction can play an important role in the industry not only to predict movie success but to help directors and producers make better decisions for the purpose of profit. This study proposes a movie prediction model that applies data mining techniques and machine learning algorithms to predict the success or failure of an upcoming movie (based on predefined parameters). The parameters needed for predicting the success or failure of a movie include dataset needed for the process of data mining such as the historical data of actors, actresses, writers, directors, marketing and production budget, audience, location, release date, and competing movies on same release date. This model also helps movie consumers to determine a blockbuster, hit, success rating and quality of upcoming movies before deciding on a movie ticket. The data mining techniques was applied to Internet Movie Database MetaData which was initially passed through cleaning and integration process.

Evaluation and Validation of a Prediction Model for Extubation Success in Very Preterm Infants

ObjectiveTo evaluate the performance of a publicly available model predicting extubation success in very preterm infants.Study DesignRetrospective study of infants born < 1250 g at a single center. Model performance evaluated using the area under the receiver operating curve (AUROC) and comparing observed and expected probabilities of extubation success, defined as survival ≥ 5 d without an endotracheal tube.ResultsOf 177 infants, 120 (68%) were extubated successfully. The median (IQR) gestational age was 27 weeks (25–28) and weight at extubation was 915 g (755–1050). The model had acceptable discrimination (AUROC 0.72 [95% CI 0.65–0.80]) and adequate calibration (calibration slope 0.96, intercept − 0.06, mean observed-to-expected difference in probability of extubation success − 0.08 [95% CI -0.01, -0.15]).ConclusionsThe extubation success prediction model has acceptable performance in an external cohort, supporting its potential utility in clinical decision-making. Additional studies are needed to determine if its use can improve outcomes.