Customer Analytics complete course is currently being offered by University of Pennsylvania through Coursera platform and is being taught by Eric Bradlow, Peter Fader, Raghu Iyengar and Ron Berman.
About this Course
In this course, four of Wharton’s top marketing professors will provide an overview of key areas of customer analytics: descriptive analytics, predictive analytics, prescriptive analytics, and their application to real-world business practices including Amazon, Google, and Starbucks to name a few. This course provides an overview of the field of analytics so that you can make informed business decisions. It is an introduction to the theory of customer analytics, and is not intended to prepare learners to perform customer analytics.
Skills You Will Gain
- Predictive Analytics
- Customer Analytics
- Regression Analysis
- Marketing Performance Measurement And Management
Also Check: How to Apply for Coursera Financial Aid
Coursera - Customer Analytics Week 2 Quiz Answers
Descriptive Analytics Practice Quiz 1 Answers
Question 1) What is a possible drawback of active data collection that should be avoided?
Survey fatigue
Low return on investment
A drop in NPS (Net Promoter Score)
All of these are correct
Question 2) Causal research methods should be used when you have which type of problem?
An ambiguous problem
A clear problem and research hypothesis
A clear problem without a hypothesis
Question 3) Which managerial question cannot be answered using only scanner data?
Will cherry pickers become loyal?
Who buys our products on promotions?
Which types of displays work better?
Which advertisement caused sales to increase or decrease
Question 4) What question is used to find the NPS?
How satisfied are you with this product?
How likely are you to buy this product again?
How likely is it that you would recommend [your company] to a friend or colleague?
Question 5) What does exploratory research help define?
Causal relationships
Areas to research in depth
The characteristics of relevant groups
Descriptive Analytics Quiz 2 Answers
Question 1) What is descriptive analytics?
Information needed for actionable decisions
Links the market to the firm through information
Systematic collection and interpretation of data
All answers are correct
Question 2) When is exploratory analysis best utilized?
When the managerial problem is ambiguous
When the managerial problem is causal in nature
When the managerial problem is descriptive in nature
Question 3) What is one problem with Marketing Research Online Communities?
Shorter deadlines are not possible
Return on Investment is quite uncertain
It does not enhance engagement with customers
Question 4) When are mobile surveys best?
For retrospective feedback
For generic context-free surveys
For context-specific, at the moment surveys
Question 5) Why do people pay so much for Point of Sales (POS) data?
Completeness of the data
Accuracy of sales information
Timeliness of marketing activity
All answers are correct
Question 6) What are some caveats with POS data?
Cannot make causal claims
Don’t know customers purchases
Don’t have information on brand-level promotions
Question 7) What is sentiment analysis?
It finds errors in any customer-level data
It quantifies the amount of promotional activity in POS data
It is frequently used in social media data to quantify the valence of information
Question 8) What is required for making the following causal statement: X causes Y?
Temporal antecedence of X
Correlation between X and Y
All answers are correct
No third factor affecting both X and Y
Question 9) What is an example of active data collection?
Surveys
Mobile data
TV viewing data
Internet surfing data
Question 10) In Net Promotor Score surveys, how much do “promoters” score on a scale of 0-10.
7,8
0-6
9,10
Customer Analytics Week 3 Quiz Answers
Predictive Analytics Practice Quiz 1 Answers
Question 1) In a simple regression formula, does R(2) represent?
The effect of X on Y
The Randomization Ratio
The strength of the regression analysis
The quality of the model’s out-of-sample forecast
Question 2) If you have a trustworthy regression line, R(2) should be at or above what percentage?
.55
1.0
0
0.7
Question 3) What is optimal pricing?
The price that yields the highest R2
The price that will maximize profits
The price that will retain the most customers
The price that creates the most satisfied customers
Question 4) What can regression analysis be used for?
Determining how independent variables affect a dependent variable
Determining how dependent variables affect independent variables
Choosing the right dependent variables to explain the independent variables
None of the above
Question 5) Given only the four choices in the table below, what is the optimal price for maximizing profit (assume cost is zero)?
5.75
6.75
2.75
1.5
Question 6) Why are KPIs important?
KPIs can indicate brand loyalty
KPIs can help determine optimal price
KPIs can predict customer behavior beyond period 2
All of the above
Question 7) What does RFM stand for?
Recency, Favorability, Marketability
Reliability, Favorability, Marketability
Reliability, Favorability, Monetary Value
Recency, Frequency, Monetary Value
Question 8) What limits the use of regression analysis?
It is not very accurate
It can only predict profits
It can only be used to determine the behavior of repeat customers
It can only be used to predict behavior over a period or two ahead
Question 9) In the data set discussed in the video “Making Predictions Using Data Sets” why are the “Sarahs” (i.e., customers who have only made one purchase) so important?
There are many Sarahs in most datasets
They represent future potential sales
They indicate the level of randomness of the data set
They can be used to determine actions that cause unhappy customers
Question 10) Why is it important to predict customer behavior far into the future?
To predict market variability
To determine customer lifetime value
To ensure that you are setting the optimal price
Predictive Analytics Practice Quiz 2 Answers
Question 1) In which of these situations would it be more appropriate to use a probability model rather than a regression/data-mining approach?
Predicting whether the customer will churn in the next year
Predicting when the customer will make her next purchase
Predicting which customer is most likely to churn in the next year
Predicting whether the customer will buy the brand at least once in the next year
Predicting the brand that the customer will buy during her next category purchase
Question 2) Which of the following are genuine data-mining procedures? (Please check all that apply)
CART
MARS
SCAN
All answers are correct
Question 3) Which of these statements is most aligned with our assumption(s) about randomness when it comes to modeling/explaining customer behavior?
Any given customer is quite predictable, but the randomness exists across customers
Customers are not truly random but appear to be “as if” random from an outsider observer’s perspective
Each customer is assumed to behave randomly in accordance with a standard normal (“bell-shaped”) distribution
Most customers are predictable but there is usually a segment of “as if” random ones that should be accounted for
We make some assumptions about randomness in order to derive the mathematical model, but when it comes to actually estimating the model they no longer apply
Question 4) Among the explanations below, which one is a reason to favor a probability model over a regression-like (e.g., data-mining) model for long-run projections of customer behavior?
Probability models can determine customer motivations
Probability models are more accurate than regression models
If the observed behavior is viewed in an “as if” random manner, it would be wrong to put it into a regression-like model as if it’s deterministically true
Regression-like models are fine for a one-period-ahead prediction, but not beyond that horizon
Question 5) Why does the “RFM” rubric present the three key measures (recency, frequency, and monetary value) in that order?
Recency is the most predictive of the three
Recency is the easiest of the three to observe/measure
There is no particular reason; it’s just an arbitrary order
This is the order in which they were discovered/identified as being highly predictive of future behavior
Recency and frequency are equally important, and monetary value is far less important than both of them
Question 6) When we refer to a “cohort,” we are talking about a group of customers who
Share similar churn propensities
Share similar purchasing propensities
Share similar acquisition characteristics (e.g., time of acquisition)
Share similar observable personal characteristics (e.g., demographics)
Share similar responsiveness to marketing tactics
Question 7) Referring back to the dataset (and model) we covered extensively, how would these two customers (both “acquired” in 1995) compare to each other, in terms of their expected future purchasing?
Vrinda would likely be more valuable
Yoshinori would likely be more valuable
They would be expected to be roughly equal
There’s not enough information here to make the decision
Question 8) What does a “BTYD” model refer to?
Buy Till You Die
Beta Time-Yield Distribution
Bayesian Transformation of Yearly Data
Back-Test Your Data
Question 9) Referring back to the dataset (and model) we covered extensively, how would these two customers (both “acquired” in 1995) compare to each other, in terms of their expected future purchasing?
Ted would likely be more valuable
Jane would likely be more valuable
They would be expected to be roughly equal
There’s not enough information here to make the decision
Question 10) Which of these real actions would not be represented by the “buy” in the BTYD model?
When a customer attends a sales event
When a customer files an insurance claim
When a customer participates in a promotional sale
When a customer renews a subscription
All answers are possibilities
Also Check: Cryptography All Weeks Quiz Answers - Coursera!
Customer Analytics Week 4 Quiz Answers
Prescriptive Analytics Quiz Answers
Question 1) What is the goal of prescriptive analytics?
Optimize a function
Develop a model to describe the data
Explain the relationship between actions and outcomes
Make a recommendation on an action that will optimize a goal
Question 2) When would descriptive and predictive results need additional analysis?
When there is competition involved
When there are strategic consumers involved
When the firm can make a choice of different actions to take
When there are multiple explanations to the same data we observe
All answers are correct
Question 3) Which one of the following is an example of a goal/objective?
The price of a product
The color of a product
The shape of a product
The quantity of a product sold
Question 4) What is an action? (Please check all that apply)
The price of a product
A choice that impacts the goal
A part of the model under the direct control of the firm
Question 5) What does a model do?
Finds a goal
Shows in a graph how price changes with quantity
Tells us how to make the maximum profit
Explain the relationship between actions and parameters to the goal
Question 6) When does maximizing revenue also maximize profit? (Please check all that apply)
When the marginal cost is zero
When there is no cost to the product
When the marginal revenue equals marginal cost
Question 7) Why does it matter to know how a demand curve was generated?
It helps find errors in the data
Correlation does not imply causation
Knowing the truth always helps
We may give a different recommendation for different models
Question 8) Which one of these is an example of a tradeoff?
Increasing the quality of a product increases it sales
Decreasing the cost of production increases profit
Showing more ads to consumers makes them buy more products
Discounts on a product brings more buyers now and makes buyers wait for discounts in the future
Question 9) Why is it important to consider strategic interaction?
It can affect the recommendations you make
You need to ensure you are asking the right question
Strategic interaction can affect the validity of your model
All of the above
Question 10) What does online retargeting do?
Show lots of ads to people
Tries to remind people to buy more
Targets consumers better with ads
Shows ads to people after they visited a specific website
Customer Analytics Week 5 Quiz Answers
Applications
Question 1) Which type of data provides the most granular level of information about a given individual’s customer behavior?
store-level data of the stores that they frequent
market-level sales from where they live
household-level scanner data from their home
aggregate tracking data for the websites that the person frequently visits
Question 2) Which of the following is the biggest challenge to solving the “advertising attribution problem”?
Most websites don’t keep a record of customer visits.
Tracking customers across digital properties is difficult
There is not enough digital advertising so that the data is sparse.
There is not significant industry interest, hence no funding available.
Question 3) When setting optimal prices, which of the following is a concern when utilizing a regression of observed sales on observed prices to set them?
Past observed prices are not randomly set.
There is not enough variation in observed prices.
Future prices might be outside the range of past prices.
All of these answers apply.
Question 4) Which of the following is not a method used to track customers across webpages?
Cookie insertion
IP address tracking
Registered user login
Pop-up advertising
Question 5) Which of the following are threats to Amazons’s use of advanced predictive shipping?
A lack of local distribution centers
Lack of data at the individual customer level
An inability to do prediction at the individual customer level
None of the answers are correct
Question 6) What technology is Comcast using to improve customer satisfaction?
GPS Tracking
Eye-tracking data
Social Network Scraping
Software that reads customer intonation
Question 7) Which of the following customers would have a higher expected customer lifetime value?
A customer who spends $100 per year, but has a 10% churn propensity per year.
A customer who spends $250 per year but has a 40% churn propensity per year.
A customer who spends $150 per year, but has a 20% churn propensity per year.
A customer who spends $200 per year, but has a 30% churn propensity per year.
Question 8) Which of the following statements are correct?
The most valuable customers to a firm in the future are those that currently spend the most.
The most valuable customers to a firm in the future are those with the highest referral value.
The most valuable customers to a firm in the future are those with the lowest propensity to churn in the future.
None of these statements is always true.
Question 9) When targeting customers for optimal marketing, which of the following rank ordering of customers from highest to lowest is most appropriate to determine which customers to target?
Highest to lowest CLV
Highest to lowest marketing effectiveness
Highest to lowest time with the firm
Highest to lowest current period spend
Question 10) Which of the following is GPS-based tracking likely to enable firms to do?
Raise CLV
Lower churn rates
Provide targeted advertisements at optimal times
All of these are correct
Post a Comment