Westcliff University K Nearest Neighbors Algorithm Questions

Part 1: (300-400 words)Explain the k-nearest neighbors algorithm for prediction, accompanied by a simple example.
Part 2: (300-400 words)
Naïve Bayes is a probabilistic machine learning algorithm based on the Bayes Theorem, used in
a wide variety of classification tasks.
1.
Please explain different types of Naïve Bayes Classifiers.
2.
Discuss advantages and disadvantages of Naive Bayes.
3.
Explain few applications of Naive Bayes.
Part 3: (1 page)
What makes a function of a discrete variable a candidate for a discrete random variable
distribution? What about the counterpart of this candidacy in the case of a continuous variable?
Explain in a one-page, APA formatted response.
Part 4:
For each investment class in Table 3, assume that future returns are normally distributed with the
population mean and standard deviation as given. Based on this assumption:
1. For each investment class, find the probability of a return that is less than zero (that is,
find the probability of a loss). Is your answer reasonable for all investment classes?
Explain.
2. For each investment class, find the probability of a return that is:
a. Greater than 5%.
b. Greater than 10%.
c. Greater than 20%.
d. Greater than 50%.
3. For which investment classes is the probability of the return greater than 50% is
essentially zero? For which investment classes is the probability of such a return greater
than 1 percent? Greater than 5%?
4. For which investment classes is the probability of loss essentially zero?
5. For which investment classes is the probability of loss greater than 1%? Greater than
10%? Greater than 20%?
Table 3
Data on Rate of Return of Investment in Securities