Maven Coffee - An Investor's Guide

Tools used in this project
Maven Coffee - An Investor's Guide


About this project


I will be playing the role of an Analytics Consultant hired by a group of investors looking to break into the US coffee market. They would like to leverage insights from "The Great American Coffee Taste Test". That's where I come in, to accomplish the task.

I have been asked to share an explanatory report providing a data-driven strategy for opening their first coffee shop. The investors expressed interest in the following areas, but are open to any additional insights and recommendations you can provide:

Target audience: What type of customer should we target, and what are their preferences?

Product offering: What types of coffee beans and drinks should we offer?

Pricing strategy: How can we align prices with customer value perception?

About the Dataset:

The data contains survey responses from ~4,000 Americans after a blind coffee taste test conducted by YouTube coffee expert James Hoffmann and Cometeer. This first-of-its-kind experiment was designed to provide a largely identical tasting experience for people across the country. After the tasting, and once the surveys were submitted, details about each of the 4 coffees they tasted were revealed.

Tools Used:

Power BI

Data Preparation & Modelling:

The data was pretty much clean but it required few changes to the column names, addition of Index column and few Pivoting to get the data to spin a story.

Data Analysis and Visualization:

Dashboard Designing - I wanted to create a dashboard that shows details from the Survey results which will be necessary for us to utilize them for our analysis. However the goal was not to create a dashboard exclusively for the survey results, hence I decided to ignore few fields and emphasize on what was necessary to answer about the potential customers, the products and beans that can be offered as well as on the pricing.

I went on to create 3 pages, one for the target audience, product offering and pricing strategy each. I also added 2 pages for the Insights and recommendations along with a welcome screen.

Insights & Analysis:

  • Target young educated adults, specifically those aged 25-34 years, who make up nearly half (49%) of the survey respondents. Cater to a predominantly male audience (62%) with a tailored in-store experience that resonates with their preferences. Factor in the majority employment status, with 67% of participants employed full-time, indicating potential for regular daily consumption and higher spending power. Be mindful of the majority racial demographic (White/Caucasian at 65%) while ensuring diversity in offerings and marketing.

  • Engaging the Educated, Employed Full-Time Segment - The coffee shop can have promotions around the routines of those employed full-time, such as "morning rush" discounts, lunchtime specials, or "after-work" sessions. Loyalty programs could also appeal to the audience.

  • While the majority of respondents identify as White/Caucasian, it's important for the coffee shop to foster an inclusive environment that welcomes all cultures and communities. This could involve a diverse range of coffee selections inspired by various coffee traditions from around the world.

  • Given the preference for a somewhat strong flavour and light roast, the coffee shop should feature a menu that highlights these attributes, perhaps through signature blends or specialty roasts. Additionally, options for personalization with dairy and non-dairy alternatives should be readily available who prefer additions.

  • Leverage the home consumption trend, with a significant preference for drinking coffee at home, suggesting opportunities for selling premium coffee beans and brewing equipment. This can include elements such as offering subscription services for fresh beans that customers can also enjoy at home.

  • The survey data presents a nuanced picture of coffee preference, with fermented Coffee D topping the charts indicating a divided consumer base (which is highly polarizing). When comparing coffees directly, Coffee D is preferred to Coffee A which is a light, washed coffee, but not overwhelmingly so, indicating that both these types have their own dedicated followings. A coffee shop that offers both can potentially capture more of the market.

  • Offer variety in coffee strength and roast, with light roasts being particularly popular, and a range of flavour profiles, with fruity and chocolaty flavours leading in preference.

  • Provide an assortment of coffee drinks with a particular emphasis on pour-over coffee, as it’s the most favoured, followed by espresso-based drinks like lattes and cappuccinos.

  • The spending data suggests a willingness among the target demographics, particularly the 25-34 age group, to spend a moderate amount in their coffee experiences, with a significant portion spending between $20-$60 per month and around $6-$10 for a cup. This indicates a consumer base that values quality in their daily coffee and is not necessarily looking for the lowest price point.

  • Customers show a range of price sensitivities, with a substantial segment willing to pay between $8-$10 for a cup of coffee, provided they perceive it as good value. Offering a pricing strategy, with options that cater to both cost-conscious (so that they feel value for money) and premium-seeking customers, could capture a wider audience.

  • There's a notable interest in home brewing, as shown by the significant numbers using pour-over and espresso methods. This enthusiasm for home coffee preparation points to a market for selling high-quality coffee brewing equipment, accessories, and workshops to educate consumers and enhance their home-brewing skills.

  • Set up a loyalty program or regular promotions tailored to the full-time employed demographic to encourage repeat visits.


This project was a great learning experience where I learnt different ways to handle analysing the multiple select questions in a survey and likewise. Also, this project was a bit tricky where we can drown and get lost in data (too many info) and choosing the right ones for the analysis was quite a learning curve.

Discussion and feedback(0 comments)
2000 characters remaining