The data is presented as a time series object which is subsequently converted into a data frame and assigned to its own unique variable. The dataset contains 2,632 rows, representing the date range of September 17, 2014 through November 30, 2021, and 6 columns (variables), corresponding to open, high, low, close (adjusted prices), and volume.

Data collected from biopsy results (positive or negative) from cervical cancer screening pool from a Venezuelan inpatient clinic. Multiple machine learning algorithms were implemented to determine whether individuals are more likely to be healthy (cancer free) or unhealthy (with positive biopsy results).

Qualitative and quantitative factors alike affect student grades. We observed 1,044 students collectively from three terms of math and language arts classes of a Portuguese secondary institution to determine which of these factors is directly influenced by performance. Student grades were tallied over the three terms, from which performance was bisected by the median and binarized into two classes of 0 and 1 (“bad”, “good”, respectively). The dataset was further subjected to an 80:20 train-test split ratio to evaluate the model performance of data outside the training set visa vie implementation of six algorithms. The C5.0 and CART models produced accuracy scores of approximately 63%; whereas logistic regression and random forest models performed approximately 1% lower in terms of accuracy. Implementation of Naïve Bayes classification in conjunction with the neural network model, yielded more accurate results of 65% and 69%, respectively. We discuss other metrics like error rate and precision and note that each model, when cross-validated, has its own limitations that may inhibit or facilitate the prediction of student performance holistically.