Q1:  Must include In-Text Citations and Scholarly references. Must be 200 – 250 words and Due by Tomorrow 8PM.

To produce valid, reliable, and reproducible results, it is important to ensure that a discovered pattern or relationship in the data is not an outcome of random chance, but rather represents a significant effect that did not occur due to natural variability in the data samples. This often involves using statistical procedures  for avoiding false discoveries. A statistical test is a generic procedure for measuring the evidence for accepting or rejecting a hypothesis that the outcome (result) of an experiment or a data analysis procedure provides.

Find a recent scholarly article involving statistical testing techniques in data mining from a credible source on the Internet or the Library (no blogs, no book chapters). Please describe the technique and the significance of the procedure in the realm of data mining and validity testing.

Here is an example of an article: Instance-Based Classification through Hypothesis Testing

The article must be published within the past three years. You must provide a direct link to the article for verification purposes.

Q2: Must include In-Text Citations and Scholarly references. 3-4 Pages and due by Thursday 8 PM.

Topic: Recommender Systems Overview: The purpose of this assignment is to explore the processes associated with Recommender Systems. Automated recommendations have become a pervasive feature of our online user experience, and due to their practical importance, recommender systems also represent an active area of scientific research. Along with the availability of new knowledge sources, including both structured and unstructured data that contain user-generated content, comes a steady stream of new systems that leverage such information to make better predictions. Recently, recommender systems have also emerged in the biomedical sciences and the objectives are the same in these applications, to predict ratings for missing items.  Recommender systems. What is a recommender system? Describe the purpose and explain how this application works to help businesses serve their target market more effectively. Also, please explain the ways in which a recommender system differs from a customer or product-based system.  Contrast with traditional systems. Please explain how a recommender system differs from a typical classification or predictive modeling system. For example, logistic regression is perhaps the most widely used statistical model for classification. It is more preferable to CF because of the ensemble feature, ability to handle missing data, and it is generally robust to noise and outliers.  Collaborative filtering (CF). Please outline one method of collaborative filtering. Please discuss why it works in the context of recommender systems and describe what its limitations are in practice. What modern techniques/systems are available to overcome these limitations? For example, memory-based algorithms can group every user with similar interests and   identify the neighbors of a new user or currently active user to anticipate the preferences of new items that would be of interest.

Include the following critical elements in your essay: I. Recommender systems: Describe the purpose and explain how this application works to help businesses serve their target market more effectively. Also, please explain the ways in which a recommender system differs from a customer or product-based system. II. Contrast with traditional systems: Please explain how a recommender system differs from a typical classification or predictive modeling system. III. Collaborative filtering: Please outline one method of collaborative filtering. Please discuss why it works in the context of recommender systems and describe what its limitations are in practice.