Elementary-Business-Analytics-Case-Book

View project on GitHub

Contents

Late Night Happy Hour

A Marketing student had a summer internship at a hotel in Waikiki. On the first day she received a spreadsheet from her boss with the revenue for sales at the hotel bar for the past 24 weeks. The marketing director asked her to analyze the “variance” in the data and determine if bar sales improved in terms of revenue and patronage after introducing a happy hour promotion on 4/1/2013 in the late night time slot from 11pm-12 midnight where all drinks were discounted 50%. The median drink price is $11.50. Average gross profit from bar sales is 75% and average net profit is 15%. Bar staff labor costs average $40/hour. She was asked to provide detailed recommendations supported by the data on continuing or changing the promotion.

Learning Objectives

  • R Studio
  • Analyzing and using experimental data

Statistics Needed

  • Hypothesis testing T-test, Anova, Tukey-Krramer/TukeyHSD
  • Normal Probability plot/(QQ-plot)
  • Unstacking data
  • Measures of central tendency, variability
  • Time series plot
  • Correlation analysis for causality

Data Source

Late night happy hour.xlsx

Tasks:

Answer the questions below to determine the actions needed to show whether having a happy hour will increase or decrease in revenue. Use the 6-step model for business analytics as a framework to answer the questions and create a final report to the Marketing Director.

Step 1. Recognize the problem

  • What are the goals for introducing the happy hour promotion?*

  1. Maximize profit from bar

  2. Increase business during slow times

    • Should the hotel in Waikiki continue to provide happy hour? If so, what days? For how long? Is late night better than other time periods? Seasonal?
  • What factors are expected to impact the profit of having a happy hour? e.g. cost of drinks, time of day, day of week

Step 2. Defining the problem

  • What might we speculate the relationship is between happy hour and revenue is?
  • Are there any possible limits withe the data that could change the results?
    • We do not have specific cost data so profit must be inferred from revenue
    • We do not have number of patrons or number of drinks sold so this must be inferred from revenue
    • We only have data from Jan to June and Happy Hour was introduced in May so we cannot remove the possible influence of season (possibly higher hotel occupancy / visitors in May-June resulting in higher bar revenue)
    • We do not have repeated Happy Hour/no Happy Hour data over arbitrary time-periods to be able to determine unbiased variability of impact and causation.
  • What assumptions must we make ro address the problem?
    • Bar patronage is independent of season
    • 2013 is typical for the hotel (e.g. no special reason that occupancy would be higher or lower than average)

Step 3. Structuring the problem

  • What are the decisions to be made? Hint: It’s not just about keeping the happy hour.

Step 4. Analyzing the problem

  • What are the factors that affect the decisions?
  • Are there useful secondary effects? e.g. Having a late night happy hour affects profits before the happy hour
  • What are some models and techniques that are needed to address the questions?
    1. What is the impact of happy hour on revenue?
    2. How does happy hour impact patronage?
    3. What is the effect of time (time-slot, day of week, month, season)?
    4. Are the impacts lasting or temporary?

Step 5. Interpreting Results and Making a Decision

  • How confident can we be in our results?
  • Do the assumptions that were made prior match the results?
  • What decisions can we make based off the results?

Step 6. Implementing the solution

  • How does the decisions that is carried out achieve the original goal of profit maximization?
  • What resources or limitations do we need to consider?

Questions to Answer:

  1. Specify the problem of the case. What are the goals for having a Late Night Happy Hour? What decisions need to be made for this case?
  2. Is the data provided in a usable format for statistical interpretation?
  3. Create a box plot to compare the groups of total revenue with Late Night Happy Hour and without. What is your first impression of looking at the revenue box plots?
  4. Create an ANOVA test to find the sum, mean, and the confidence interval to determine how confident you are in the comparison between the two variables. The results will provide a clear assumption of the data.
  5. Are there any changes in your initial assumption of the box plots after analysis?
  6. Does greater sales always equate to greater revenue?

Report

Write a professional report (as if you were a hired consultant or employee) for the Marketing director. The report should be to the point and give specific, actionable advice or solutions based on the data and analytics. Avoid technical aspects and terms that are non-essential and any speculations not substantiated by the data. This report should be concise and to the point without lengthy explanations being necessary to understand it.

There is no min or max page limit as charts and tables can take up a highly variable amount of space. However, any charts or tables included need to be understandable to a layman at first glance. The particular models you use, interpretations, and advice given are your choice and you should be prepared to explain or defend this if needed!

Use this as an outline for the report:

A. Description of the business problem

  • What would influence whether or not to continue happy hour?
  • What are the key decisions that need to be made to enact the improvements? Indicate specifically what the options are (or give examples of options).
  • Why are your findings important?
  • What questions will be answered and how do these explicitly help address the decisions?

B. Data, methods, and models and results

  • Discuss the basic approach used to analyze the data and any concerns about the integrity and quality of the data used. e.g. “There is concern about the increased revenue of happy hour because revenue was not part of the data set. There is insufficient data to assume more profit will always equal more revenue.”
  • Briefly describe the models used (formulas, tables, graphs) indicating what they are used for (try to avoid technical details) e.g. “This calculation determines the individual effects of x and y on z to see which variable affects z more.”
  • Provide detailed answers to the decision questions using the models
  • Indicate all “important” assumptions made and why you think they are reasonable. An assumption is important if: you need it to get a result e.g. “To understand the affect time has on profit we assumed the time block of 11:00-11:15 was meant to be 11:00-12:00.” the assumption, if wrong or invalid, would significantly affect your results. e.g. the assumption “There will be an equal number of customers coming every month”. If wrong or invalid, would significantly affect what prices could be set and the advertising amounts that would be needed.
  • Do not list technical assumptions used for statistical analysis e.g. “We assume the sales data is Normally distributed.”

C. Decision making

  • Explain specifically how you used the models and results to make your decisions. This may be literal results such as “Having a happy hour will increase profits for x days of the week.”
  • Detail special considerations or issues to watch out for e.g. “There is not enough data to calculate yearly profit so any profit will be calculated by week.”
  • Describe how the effects from using the results for making the decisions can be measured or observed. i.e. How can the company know that profits are being maximized? How can management measure the success of the changes?