Bellabeat Case Study

Introduction:

Bellabeat is a high-tech company that creates smart health solutions for women. The Bellabeat app and a variety of smart gadgets collect data on activity, sleep, stress, hydration, and reproductive health in order to provide women with a better understanding of their own health and behaviors. Urška Sren and Sando Mur started the company in 2013, and it has grown rapidly since then, with the potential to become a major participant in the global smart device industry.

Bellabeat's product line includes the Bellabeat app, which provides data on users' exercise, sleep, stress, menstrual cycle, and mindfulness habits in order to provide insight into their health. The Bellabeat app is also compatible with the company's smart device line.

Business Task:

Analyze smart device usage data in order to gain insight into how consumers use non-Bellabeat smart devices.

Questions for the analysis:

• What are some trends in smart device usage?

• How could these trends apply to Bellabeat customers?

• How could these trends help influence Bellabeat marketing strategy?

Key Stakeholders:

• Urška Sršen — Bellabeat’s co founder and Chief Creative Officer

• Sando Mur — Mathematician and Bellabeat's cofounder; key member of the Bellabeat executive team

• Bellabeat marketing analytics team — A team of data analysts responsible for collecting, analyzing, and reporting data that helps guide Bellabeat’s marketing strategy.

Prepare:

FitBit Fitness Tracker Data on Kaggle will be used for this analysis. Between 03.12.2016 and 05.12.2016, responders to an Amazon Mechanical Turk distributed survey created these 18 datasets. Thirty Fitbit users who met the criteria agreed to have their personal tracker data submitted, which included minute-level output for physical activity, heart rate, and sleep tracking. Export session ID (column A) or timestamp can be used to parse individual reports (column B). The variation in output represents the use of various Fitbit trackers as well as individual tracking practices and preferences.

Because of the small sample size and the lack of essential participant variables such as gender, age, location, and lifestyle, this data has limitations.

Installing and Loading Packages:

Example:

Process:

Inspecting data frames:

To make sure the data frames were imported properly, the head() function was used. The functions colnames() and glimpse() functions were used additionally to explore the data frames and find similarities.

daily_calories:

daily_intensities

daily_steps

heart_rate_sec:

minute_METS:

sleep_day:

weight_log:

Removing data frames:

All the date frames contained the “Id” column. This makes it possible to merge the data frames together if needed. The data frame, daily_activity, contains data for calories, intensities, and steps. The goal is to ensure the number of observations match between daily_activity and daily_calories, daily_intensities, and daily_steps.

Since the data needs to be validated for integrity, it is important to use an additional data validation tool. For this, SQL was used to validate the findings. Sqldf was installed into R Studio to ensure a smoother transition when looking at the data. This allows for temporary data frames to be visualized and validated.

The data output from the temporary data frame using the head() function matches the data output from the original data frame using the head() function. The data from the SQL data frames also matches the data from the original and temporary data frames. The number of rows from the SQL is 932. This number of rows matches the number of rows from the daily_calories, daily_intensities, and daily_steps. To ensure there is no confusion with the analysis these data frames will be taken out.

Analyze:

Summarize the data:

The n_distinct() and nrow() functions are used to determine the number of unique values and the number of rows in a data frame, respectively.

The data frames in weight log and heart rate are composed of a small number of participants. With this low number, a conclusion cannot be reached solely based on these data frames.

The summary() function was used to extract key statistics from each data frame.

daily_activity:

The regular user takes 7638 steps per day, falling short of the CDC's suggested 10,000 steps for good health. Users spend an average of 21.16 minutes per day doing highly energetic or intense activity, which corresponds to 148.12 minutes per week. The Centers for Disease Control and Prevention recommends 75 minutes of vigorous activity each week, so the average Fitbit user is meeting this recommendation and reaping additional health advantages. Participants, on the other hand, spend an average of 991.2 minutes a day sitting, or 16.52 hours per day! Because the body functions best upright, this is a large amount of time that can lead to numerous health difficulties. Scientists discovered that 40 minutes of moderate to intense activity per day can counteract the negative effects of sitting for up to 10 hours per day. Furthermore, the average user burns 2304 calories each day, according to this report. According to studies, the average person burns 1800 calories every day, while 3500 calories are required to shed a pound of weight. In this situation, Fitbit users are burning more calories than usual, and are on schedule to shed a few pounds per week if they so desire.

heart_rate:

The average heart rate of 77 beats per minute (bpm) is within the "normal" range, despite the limited number of users in the heart rate data frame. Men's heart rates should be between 50 and 80 beats per minute, while women's heart rates should be between 53 and 82 beats per minute. However, research suggests that determining what is a normal and healthy heart rate for an individual, rather than comparing to population values, is more significant. This is because resting heart rates can differ by up to 70 beats per minute between people. Changes in resting heart rate over a period of days could indicate an infection, the effects of the menstrual cycle, or other acute events. As a result, heart rate has become an important health metric to track.

minutes_METS:

A MET is a ratio of your working metabolic rate relative to your resting metabolic rate. Metabolic rate is the rate of energy expended per unit of time. To put it in perspective, a brisk walk at 3 or 4 miles per hour has a value of 4 METs. Jumping rope, which is a more vigorous activity, has a MET value of 12.3. The summary of the minute_METs shows the average user has a MET of 14.69. Having a MET of 14.69 compared with the 12.3 used with jumping rope, shows that the average user does very high vigorous activity. This makes it hard to use this data in the analysis because it appears the activity tracker is not tracking accurately. This data will not be used in the final analysis.

sleep_day:

The typical user sleeps for 419.5 minutes each day, or nearly 7 hours, according to the summary of the sleep data frame. This is in line with the CDC's guidelines for adults in order to obtain enough sleep. The average participant spends 458.6 minutes (7.64 hours) in bed. This suggests that the average user is awake in bed for 38.6 minutes. People should not spend more than one hour awake in bed, according to Health Central. This is done to avoid the formation of a mental link between being awake and being in bed, which might lead to insomnia.

weight_log:

Despite the small number of participants in this data frame, the average BMI is 25.19. This is a BMI that is considered overweight. BMI, on the other hand, can be used as a screening tool and does not diagnose an individual's body fatness or health.

Share:

In order to export the data, I used write.csv2 to export the data to document form to better import into Tableau.

Act:

Since its inception, Bellabeat has been successful in empowering women by delivering statistics on their activity, sleep, stress, hydration, and reproductive health. Recommendations for Bellabeat's future expansion can be made based on an analysis of how Fitbit users utilize and respond to features.

The Bellabeat app should be redesigned and modified. Rather than simply giving health statistics, the app should inspire users to achieve fitness objectives and serve as a social networking platform.

Working out with a friend can help one feel more inspired, be more adventurous in attempting new activities, and become more consistent, according to the CDC. The CDC even suggests using a social media workout app to stay in touch with pals while achieving your goals. Having a community of supportive women ready to prioritize their health could make the Bellabeat app social media workout app for women.

Recommendations for Bellabeat app:

• Allow consumers to share their favorite workouts, wellness advice, and healthy foods via social media.

• Allow people to add pals and see what they're up to.

• To promote utilization, create weekly exercise and wellness challenges.

• Make fitness and health-related businesses pay for advertising.

• Encourage consumers to do 10,000 steps per day and enable alert notifications to help them achieve their goal.

• Recommend that users get at least 7 hours of sleep per night, and activate alert messages to motivate them to do so.

• Recommend that users get 75 minutes of vigorous movement every week, and allow entourage users to receive alert alerts to help them reach this goal.

• Encourage people to track their BMI by entering their weight and height.

• If users want to lose weight, enable notifications to remind them to burn the calories they need to reach their goal.

• If the user's resting heart rate differs significantly from usual, enable alarm alerts.

• Enable notifications to encourage users to get out of bed if they've been awake for an hour.

• If a user has been inactive for a lengthy period of time, enable notifications to encourage them to get moving.

Works Cited:

“3 Reasons to Work out with a Friend.” Centers for Disease Control and Prevention, Centers for Disease Control and Prevention, 23 Apr. 2021, www.cdc.gov/diabetes/library/spotlights/workout-buddy.html

“About Adult Bmi.” Centers for Disease Control and Prevention, Centers for Disease Control and Prevention, 17 Sept. 2020, www.cdc.gov/healthyweight/assessing/bmi/adult_bmi/index.html

“CDC — How Much Sleep Do I Need? — Sleep and Sleep Disorders.” Centers for Disease Control and Prevention, Centers for Disease Control and Prevention, 2 Mar. 2017, www.cdc.gov/sleep/about_sleep/how_much_sleep.html

“The Dangers of Sitting: Why Sitting Is the New Smoking.” The Dangers of Sitting: Why Sitting Is the New Smoking — Better Health Channel, 22 Aug. 2020, www.betterhealth.vic.gov.au/health/healthyliving/the-dangers-of-sitting

Gornall, Lucy. “How to Lose Weight: How Many Calories Should i Eat to Lose Weight?” GoodtoKnow, 12 Aug. 2020, www.goodto.com/wellbeing/diets-exercise/what-is-calorie-how-many-lose-weigt-425557

Grey, Heather. “Heart Rates Can Vary by 70 Bpm: What That Means for Your Health.” Healthline, Healthline Media, 9 Feb. 2020, www.healthline.com/health-news/what-your-heart-rate-says-about-your-health

“How Much Physical Activity Do Adults Need?” Centers for Disease Control and Prevention, Centers for Disease Control and Prevention, 7 Oct. 2020, www.cdc.gov/physicalactivity/basics/adults/index.htm

Nield, David. “Scientists Figured out How Much Exercise You Need to ‘Offset’ a Day of Sitting.” ScienceAlert, 26 Nov. 2020, www.sciencealert.com/getting-a-sweat-on-for-30-40-minutes-could-offset-a-day-of-sitting-down

Reed, Martin. “Spend Less Time In Bed If You Want More Sleep.” Healthcentral.com, 7 May 2017, www.healthcentral.com/article/spend-less-time-in-bed-if-you-want-more-sleep

Roland, James. “What Are Mets, and How Are They Calculated?” Healthline, Healthline Media, 21 Oct. 2019, www.healthline.com/health/what-are-mets#calculation