Coffee Shop Business Analytics Project – Introduction to Business Analytics,Individual Assignment, Ireland

Coffee Shop Business Analytics Project

Background

You have been hired as a consultant data analyst for a co4ee shop experiencing rapid growth. The co4ee shop o4ers both take-away and a delivery service. The co4ee shop owner has no knowledge of analytics, but has heard of the potential that analytics can bring to a business. They are eager to understand if they can leverage data analytics to enhance decision-making processes, optimize operations, and improve customer satisfaction. They have provided you with datasets containing various aspects of their business operations over the recent years.

Dataset Description

Two datasets are provided.

The first dataset contains event log data from 2018 (event_log.csv), that can be used for process mining. This data contains three fields, namely, the `Case Key`, `Event time` and the name of each `Activity`.

The second dataset contains 12 weeks of historical data from 2019 (12_weeks_co3ee_shop_data.csv). This includes hourly information on the customer demand (number of orders), and the total required delivery distance per hour, etc.

Assignment Tasks

Your assignment consists of producing a 5-page Data Story about the business. This should be created using Powerpoint (or similar).

Each page of the data story should “stand on its own” as a self-contained story. In other words, the co4ee shop owner could pick up any page at random and the contents of the page are self-explanatory to the owner. Also note here, the co4ee shop owner is your target audience / business stakeholder. Please follow the guidelines below on what needs to be covered in each page:

1. Cover Page (Page 1)

The cover page should be engaging and professional. At a minimum it should include a data story title, your name and the date.

2. Process Mining and Descriptive Analytics (Page 2)

Given the event log data (event_log.csv):

– Perform a basic process mining analysis using the `Case Key`, `Activity` and `Eventtime` variables.

– Map out the typical order fulfilment process.

– Summarize key statistics.

– Use process flow diagrams to visualize the steps.

– Identify the variants, and any bottlenecks, deviations, or ine4iciencies in the process flows.

– Highlight any opportunities arising for the business.

3. Predictive Analytics (Page 3)

Given the 12 weeks of historical co4ee shop data (12_weeks_co3ee_shop_data.csv):

– Create hourly forecasts of customer orders over the next three weeks.

– Identify trends in the forecast data, including high and low volume periods, etc.

– Provide error statistics relating to the forecast model based on the 12 weeks of historical data.

– Highlight implications for the business.

4. Prescriptive Analytics (Page 4)

Using the forecasted data generated in Section 3, identify the day with the highest total customer demand. Based on the forecasted hourly customer order values, calculate the Total_Delivery_Distance per hour by simulating the average customer delivery distance and multiplying it by the number of customers orders per hour.

For that day, use the hourly forecasted delivery demands and simulated delivery distances to formulate and solve an optimization problem. The objective is to minimize the total cost of hiring couriers while ensuring that the forecasted delivery demands (Total_Delivery_Distance) are met. Formulate the optimization problem based on the following specifications.

Objective:
Minimize the total daily cost of hiring couriers for a co4ee shop delivering within a 10- mile radius.

Specifications:

a) Courier Cost: Each courier charges €15 per hour.

b) Courier Capacity: Each courier can cover up to 25 miles per hour.

c) Delivery Range: Deliveries are within a 10-mile range.

d) Max Couriers: A maximum of 10 couriers can be on shift at any one time.

e) Operating Hours: The shop is open from 7 AM to 7 PM (12 hours of operation per day).

f) Delivery Requirements: The total delivery distance required per hour is based on customer demand and is a key input to the optimization problem.

Present and summarise the recommendations (number of couriers on shift per hour) and the optimal objective function value. Provide any other information you feel is relevant.

5. Summary and Overview (Page 5)

Summary of Findings:
-Provide a concise summary of the key insights and recommendations from your descriptive, predictive and prescriptive analyses.

– Emphasise how these insights and recommendations address the business objectives outlined in the introduction.

– In the spirit of a data story this page, like the four earlier pages, should be largely visual in nature.