Questions tagged [marketing]
For on-topic questions about statistics or machine learning used in marketing or market research.
168
questions
0
votes
0
answers
21
views
Budget allocation using multiplicative regression model
I need your help to define the optimal budget allocation using a marketing mix model. I have built a multiplicative model to account for diminishing return and interaction between my IVs, and I am ...
0
votes
1
answer
23
views
Question about mix marketing modeling (MMM)
I am working on multiple regression in order to realize a marketing mix model. However I have some concerns with the procedure. First, the idea of transforme data in order to incorporate the carryover ...
0
votes
0
answers
10
views
Determining statistically significant responses in a research - Likert scale answer by 3 customer groups. which responses are significantly diff?
I have research in which I asked a question from 3 different customer segments on a likert scale.
how can I find out if I am more likely to spend money on binge shopping on a particular day?
|Cust ...
0
votes
0
answers
323
views
How do I interpret negative SHAP values for a marketing model?
I am building a marketing model to evaluate marketing channel effectiveness. My inputs are the marketing spend for each channel, and my target variable is sales. I have 3 years of weekly data in ...
0
votes
0
answers
20
views
Any other machine learning algorithms besides clustering for Customer Segmentation
I've searched online materials for Customer Segmentation for a while. Most materials are related with K-means or some other clustering algorithms. Are there any other machine learning or statistical ...
1
vote
0
answers
54
views
Validity of modelling different ordinal variables via linear regression
I am attending a course in Marketing. Our latest assignment was to analyze data from a survey regarding dishwashing detergents. The questions we asked respondents were all of an ordinal kind: they had ...
0
votes
0
answers
32
views
Length of Pre and Post Period
A colleague and I have a disagreement on the length of the pre period in a pre vs. post analysis. We are measuring year over year change in sales of a marketing change we made in Sept last year. For ...
1
vote
0
answers
63
views
Multicollinearity Market mix modeling
I want to know what can be the best approach to handle multicollinearity. I am building a regression model with just 4 independent but all important variables and am not able to control the VIF.
...
0
votes
0
answers
88
views
Standard procedure to approach Linear Regression with data having different granularity
The goal of my analysis is to estimate a model that explains the Sales as a function of my marketing and media variales. I have available weekly data but with different granularity.
My dataset is ...
0
votes
1
answer
30
views
Trying to find the appropriate statistical method(s) to answer a marketing question — analyzing composition of groups
I’ve got roughly 90k rows of data, where each one represents a customer at my company. One of the columns tells me the channel that brought that customer to my company.
I’m looking at the channel mix ...
0
votes
0
answers
11
views
Looking for statistical modeling approaches/examples for "difference in cost per click/conversion" on Facebook split tests
Mainly looking for references to articles, guides, and vignettes that tackles this or similar problems, thanks!
Trying to find the best modeling approach for Facebook ad data. I want to model 'cost ...
0
votes
0
answers
62
views
What Statistical/ML methods are best to solve digital marketing budget optimization?
In our company we want to optimize our digital marketing budget spending i.e. given a budget $B$, we want to allocate it efficiently to marketing channels ${C_1, C_2, C_3,.., C_n}$. Some example of ...
0
votes
0
answers
170
views
Calculating contribution in sales by each predictor variable in log-linear multiple regression model
I am working on Market Mix Model in R. I have weekly data. I have earlier built a additive model i.e a level-level regression model between the sales(dependent variable) and marketing input, ...
0
votes
0
answers
26
views
Testing multiple landing pages simultaneously
Let's say we are wanting to test the conversion rate for multiple landing pages. To be safe, we must allocate 50% of our traffic to our current "champion" page. We then have 8 "...
1
vote
1
answer
162
views
RFM Customer segmentation - Why Avg monetary value instead of total monetary value?
I am trying to segment our customers based on their purchase data. And I came to know about the RFM technique (Recency, Frequency and Monetary) through these posts here, here etc.
Recency - How ...
0
votes
0
answers
100
views
Uplift modeling with targeted experimental data
I am trying to set up a marketing campaign for cross-selling purposes of a specific product. Since the campaign has already been launched on a subset of customers, based on certain characteristics ...
0
votes
1
answer
110
views
Binomial test with Chance level prediction
Thanks for reading.
I wanted to ask if my logic I used for my experiment makes any sense.
My hypothesis is that watching Pepsi commercial increases Pepsi preference.
My experiment has 2 steps.
(1) ...
1
vote
1
answer
40
views
Binary classification supervisor definition help
I need help with defining the supervisor for a ML model.
Background: I’m predicting if a customer will respond positively to a marketing campaign. The response is a binary variable that I am given at ...
0
votes
0
answers
70
views
Modern MMM implementations?
I have been working with my company's Marketing Mix Modeling solution for years now. We are looking to update our modeling methodology and are looking at different options. What are the current 'up-to-...
0
votes
1
answer
47
views
Need help choosing appropriate algorithm for building a Lookalike audience
Newly practicing data scientist here! I am currently stumped on a project and reaching out for some guidance:
I am working with the marketing team in our customer database. There is a small subset of ...
1
vote
1
answer
56
views
Is this a statistical test ? what is the experimental unit? and how to treat dependency between observations?
I'm trying to understand which statistical test to use and what is my experimental unit?
The problem:
We have a budget algorithm that moves the budget between 10 different ad campaigns and tries to ...
1
vote
0
answers
501
views
How to derive sales contribution in a log-log regression media mix model?
I am working on a media mix model to determine how different media channels impact sales.
Since there is a non-linear relationship between sales and media spend, I needed to apply a log transformation ...
1
vote
0
answers
88
views
How to create bayesian test for ROI/ROAS metric
I am interested in using A/B Bayesian testing to compare ROAS for marketing scenarios.
I've seen references dealing with cases such as:
Using a beta distribution prior to model a binomial-distributed ...
1
vote
1
answer
86
views
Calculating Average Days Between Customer Orders - Exponential Distribution?
I have detailed sales data including customer number, SKU, product line, and order date. For marketing purposes, I would like to know the average days between orders both on a per-customer, per ...
0
votes
0
answers
39
views
Marketing ROI: Modelling media budget impact on first choice, relevant set (over time)
I want to analyze a dataset with longitudinal data collected over three years.
Each month n = 200 randomized people (edit: new sample each month) are asked a small set of evaluative questions (brand ...
1
vote
0
answers
15
views
Appropriate statistical procedures to compare sales based on Internet search keys
This is my first question ever on Stats StackExchange and I am hoping to get some guidance from the community.
I have graduated with a BSc in Statistics, so I am familiar with the fundamentals of ...
0
votes
1
answer
20
views
Is there any meaning to using several validation metrics in cross validation for logit models?
My question might be a bit dumb since I'm relatively new to analysises using k-fold CV, but here goes:
I want to compare two logit models using k-fold CV, and then compare with another model type on a ...
0
votes
0
answers
98
views
Influence of TV spots on the number of visits to the website (time series problem)
I have hourly data regarding the number of visits to the website. A single record consists of date, time(0-23) and number of visits. In a separate table I have data about the display of advertising ...
2
votes
1
answer
409
views
BTYD R package. Why dropping the first puchase in the BG/NBD model?
I am using the BTYD package on R to estimate the probability of a customer churning after my calibration period. At the moment, I have been following the walkthrough provided on the web which you ...
1
vote
2
answers
159
views
Email marketing campaign test design
We are designing an email campaign with multiple email touch points. And we are trying to understand the incremental value of each additional touch point. Our experimental design will be that the ...
1
vote
2
answers
649
views
Why do Pareto/NBD models require custom likelihood functions in PyMC3 and Stan?
I'm interested in Bayesian modeling of customer lifetime value (CLV), preferably via PyMC3. I've found that research in this area started mid-to-late 1900's and has remained active since. It would ...
3
votes
1
answer
62
views
How do i calculate if the difference between two advertisement campaigns is significant?
My brother has asked me if I can evaluate if his advertisement campaigns yield significantly different results. It was a couple of years ago I dealt with these kinds of problems, so would appreciate ...
1
vote
0
answers
47
views
How can I attribute how much sales volume came from each medium in a log-log market mix model?
So I started off with this regression equation:
$$
sales = \beta_{d}*{(ds_{t} + (ar_{d} * ds_{t-1})})^a_{d} + \beta_{tv}*{(tv_{t} + (ar_{tv} * tv_{t-1})})^a_{tv} + \beta_0
$$
Where $ds$ is the amount ...
5
votes
1
answer
759
views
Poisson regression for market media modeling?
I put together a related question linked for added context; it generally overviews a model proposed by Google in 2017 for (Marketing) Media Mix Modelling (MMM.) The model updates the pretense of MMM ...
7
votes
1
answer
2k
views
PyMC3 implementation of Bayesian MMM: poor posterior inference
Google released a whitepaper on Media Mix Modelling (MMM) in 2017; vanilla MMM (established in the 1960s) uses multivariate regression. It's a decent mechanism to understand which of your marketing ...
0
votes
0
answers
19
views
How to compare and evaluate different business concepts?
Don't ask me how exactly I came up with this question but I wonder about the following:
Assume you want to compare different offers in how requested (and/or how profitable) they are. In addition, due ...
0
votes
1
answer
422
views
How can I improve the CLV accuracy from lifetimes model?
Not sure whether this should be asked in StackOverflow or here, but I believe this question is most about statistics, so I'll try it here.
So I was modelling the Customer Lifetime Value using ...
2
votes
1
answer
83
views
Bayesian Multiple Item Response Models?
I am trying to extend the ideas of item response theory to multiple responses. Consider a marketing survey, which asks customers, "what's the deciding factor in whether or not you purchase ...
0
votes
1
answer
552
views
Market Mix Modeling using Random Forest
I am trying to build a random forest-based market mix model, wherein I want to calculate the contribution of each of my X variables towards the target. Typical MMM problem statement, but here am not ...
0
votes
1
answer
232
views
Bayes theorem in advertising [closed]
I am new to Bayes theorem, and was wondering if anyone can guide me through this question.
An advertising agency want to analyze the advertisements for a product. They want to target people from all ...
2
votes
1
answer
674
views
Design of experiments and building a logistic-regression-like model
Consider a population characterized in terms of a small number of categorical features (age category, income bracket, gender, level of education, etc.). I am interested in how these features affect ...
0
votes
0
answers
232
views
Modelling Funnel data with a regression approach
I have the following marketing dataset:
Two years of weekly brand from the YouGov BrandIndex, based on a survey. It includes
Awareness
Consideration
Purchase Intent
Sales
Media Invest into Channel 1 (...
0
votes
0
answers
168
views
Using macroeconomic variables in Market Mix Model
I am building a market mix model from proprietary data to predict sales. I would like to include macroeconomic variables as well, such as unemployment rate and consumer confidence.
However, the ...
1
vote
0
answers
36
views
Choose t-test or ANOVA for personalized ad effectiveness within each cohort?
I've got 10 cohorts(determined by ML clustering) of customers I can target for customer personalization ads.
The experimental design is that I send out a known standard personal ad(based on cohort ...
0
votes
0
answers
73
views
T-test for marketing data in excel
I am currently running an A/B test, and I’m not sure how I should be arranging my data to run a t-test in excel. I have 1 control and 2 variations that I am running for an advertising campaign - the ...
1
vote
0
answers
24
views
marketing hypothesis test sample size calculation
I am trying to design a coupon promotion test to measure the increase in the volume of orders from promotion versus no promotion. To do so, I want to calculate the pre-group sample size required to ...
10
votes
2
answers
4k
views
Poisson Gamma Mixture = Negative Binomially Distributed?
This paper introduces a model called "Beta-Geometric / NBD" which models "repeat-buying behavior in settings where customer “dropout” is unobserved: It assumes that customers buy at a ...
2
votes
1
answer
700
views
Sample Size Calculation - Two Independent Means
I am trying to design an email test to measure the demand lift obtained from a marketing promotion (treatment) versus no promotion (control). To do so, I want to calculate the per-group sample size ...
3
votes
2
answers
63
views
Email open-rate test
We ran an AB test for four days, sending our clients the same emails but with different headings, in order to know which header logic is better (i.e. has has the highest Open Rate (OR) = openings/ ...
1
vote
0
answers
23
views
It is possible to use Time series to predict wether a marketing action is a success or not
Is it possible to use time series could be used to forecast the implementation of an offer ?
Following I am describing an example about how to implement that, is it valid?
Can I use ARIMA time series ...