We are performing the analysis of data of an online shopping site.

Please refer to the dataset mentioned in this link

The fields of the dataset are:

enter image description here

We have been asked to do the following:

Perform analysis of the data using Naive Bays and Nearest Neighbours models to predict the following:

1)What is the discount percentage of a product for a given product category and brand.

2)Whether or not the product is a Flipkart Advantage Product given product category and brand.

Soln to Q1:

We can find the percentage of discount for each of the data. And also plot the probability density curve of the discount.

We can also find the mean and the median of the data.

Now, after that what we shall do?

Soln to Q2:

We can find the answer to the second question by KNN and K-Means Clustering algorithm.

Is there any way to find the answer to the second question by naive Bayes method?

For instance:

$$ P(isAdvProd/product's Data) = \frac{P(product's data/isAdvProd)*P(isAdvProd)}{P(product's Data)}$$

$$=\frac{P(isAdvProd)*P(category/isAdvProd)*P(brand/isAdvProd)}{P(product's Data)}$$

The problem here is that can $P(category/isAdvProd)$ and $P(brand/isAdvProd)$ be calculated? Cause category and brand both take 'categorical data'.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.