Place your name on all pages. Number appropriately, and solve on your paper. You must show all work to receive credit. Answer according to methods presented in the class or textbook. Partial credit is possible. Your 2 hr 20 minute exam time officially begins after you are authenticated. The first question of the exam is below. ———————————————————————– (5 pts) Let the regression equation be given by yL=12x+74{“version”:”1.1″,”math”:”yL=12x+74″}, where x{“version”:”1.1″,”math”:”x”} represents the number of books read and yL{“version”:”1.1″,”math”:”yL”} represents predicted IQ.  Determine approximately how many books were read for a predicted IQ of 158.

How does TF-IDF improve upon Bag of Words?

Which of the following words would likely have a high TF-IDF score in a dataset of customer reviews about electronics?

An HR department is analyzing job descriptions. To improve keyword searches, their system converts all text into lowercase, removes punctuation, and eliminates extra spaces.  What preprocessing step is this?

A media company is processing news articles.  To reduce redundant words, they convert different forms of “publishing,” “published,” and “publisher” to “publish.”  What preprocessing step is this?

Which of the following is not a typical step in text preprocessing?

What does tokenization do?

What is the primary goal of a classification model in machine learning?

A human resources department at a multinational corporation is revising its salary structure.  They want to predict employee salaries based on inputs like experience, education, and role to ensure fairness and competitiveness in the market.  What machine learning technique should they use?

A real estate company is developing a tool to assist agents in setting competitive listing prices for homes.  They want to predict the selling price based on inputs, such as location, square footage, and number of bedrooms.  What machine learning technique should they use?