We are evaluating new product offerings for our customers and are evaluating how our customers are reacting to these new products. We have run a test for one month and are ready to measure the results. These products have high visibility with executives at SiriusXM. The results of this test will have significant implications for what products the company will promote, at what price, and to whom.
You have been given two datasets—one containing 10000 customer and sales observations, and the other containing a lookup of product revenue by outgoing codes – with the following fields:
CustomerID – unique identifier for the customer
Product – which product the customer was offered. We want to test performance amongst three products.
InteractionDate - the date the customer interacted with SiriusXM
Revenue - actualized revenue from the product offered. We want to use this metric to measure product performance.
SalesFlag - indicator for whether the customer purchased the product. We want to use this metric to measure product performance.
SalesLikelihoodModelScore - this is a predictive model that forecasts sale likelihood for each customer. The scores are discrete and ordinal. Scores closer 0 indicate low sale likelihood; scores closer to 20 indicate high sale likelihood.
RevenueModelScore - this is a predictive model that forecasts how likely a customer is to be high revenue (score=1) or low revenue (score =10). The scores are discrete and ordinal.
NumPriorSales - the number of purchases the customer has made in the past
CustomerGeneration – this refers to the age of the customer. The categories are: Mature (born before 1945) Boomer (born 1946 to 1964), Gen X (born 1965 and 1980), Gen Y (born 1981-1996), Gen Z (born 1997 and later)
Outgoing_code – this code links customer and sale data to the revenue of purchased product
Please compile a presentation (PowerPoint, Google Slides, or equivalent) to present to the SiriusXM team that explores product performance. Be sure to cover the following in your presentation:
1. Was the test randomly administered to customers? Meaning, are the “same” types of customers receiving each product, and are the results therefore directly comparable? Provide evidence to support your claim.
2. Compare differences in revenue among products. Which products perform best? Please comment on your confidence in the differences.
3. Compare differences in sales rates among products. Which products perform best? Please comment on your confidence in the differences.
4. Are results stable? Do they drift over time? Provide evidence to support your claim.
5. Are our revenue and sales models effective at rank-ordering sales and revenue respectively? Provide evidence to support your claims
6. Comment on performance differences among generations and number of prior sales, if any exist.
7. Build a model to predict SalesFlag using the data in this dataset. Evaluate your model – does it do well at predicting sales? How would you improve the model?
You do not need to address each question in order in your presentation - you may follow 1-7 above, but we leave it up to you to decide what flow works best.
Please use Python or R to create results - you will need to submit your code along with your presentation deliverable.
Please create visualizations as you deem necessary to answer each question using Python/R
You may format tables in Excel, but you must create the underlying data in Python/R.
Item sold by Categories
If you need any programming assignment help in machine learning using R & Python, or need solution of above problem then we are ready to help you.
Send your request at email@example.com and get instant help with an affordable price.
We are always focus to delivered unique or without plagiarism code which is written by our highly educated professional which provide well structured code within your given time frame.
If you are looking other programming language help like C, C++, Java, Python, PHP, Asp.Net, NodeJs, ReactJs, etc. with the different types of databases like MySQL, MongoDB, SQL Server, Oracle, etc. then also contact us.