In this step, we define the problem and objectives of our case study and its desired outcome.
Bellabeat is a high-tech manufacturer of beautifully-designed health-focused smart products for women since 2013. Inspiring and empowering women with knowledge about >their own health and habits, Bellabeat has grown rapidly and quickly positioned itself as a tech-driven wellness company for females.
The co-founder and Chief Creative Officer, Urška Sršen is confident that an analysis of non-Bellebeat consumer data (ie. FitBit fitness tracker usage data) would reveal more opportunities for growth.
Analyze FitBit fitness tracker data to gain insights into how consumers are using the FitBit app and discover trends for Bellabeat marketing strategy.
-
What are the trends identified?
-
How could these trends apply to Bellabeat customers?
-
How could these trends help influence Bellabeat marketing strategy?
-
A clear summary of the business task
-
A description of all data sources used
-
Documentation of any cleaning or manipulation of data
-
A summary of analysis
-
Supporting visualizations and key findings
-
High-level content recommendations based on the analysis
-
1.5 Key Stakeholders:
-
Urška Sršen: Bellabeat’s cofounder and Chief Creative Officer
-
Sando Mur: Mathematician, Bellabeat’s cofounder and key member of the Bellabeat executive team
-
Bellabeat marketing analytics team: A team of data analysts guiding Bellabeat’s marketing strategy.
In the Prepare phase, we identify the data being used and its limitations.
-
Data is publicly available on Kaggle: FitBit Fitness Tracker Data and stored in 18 csv files.
-
Generated by respondents from a survey via Amazon Mechanical Turk between 12 March 2016 to 12 May 2016.
-
30 FitBit users consented to the submission of personal tracker data.
-
Data collected includes physical activity recorded in minutes, heart rate, sleep monitoring, daily activity and steps.
-
Data is collected 5 years ago in 2016. Users’ daily activity, fitness and sleeping habits, diet and food consumption may have changed since then. Data may not be timely or relevant.
-
Sample size of 30 FitBit users is not representative of the entire fitness population.
-
As data is collected in a survey, we are unable to ascertain its integrity or accuracy.
A good data source is ROCCC which stands for Reliable, Original, Comprehensive, Current, and Cited.
Reliable — LOW — Not reliable as it only has 30 respondents
Original — LOW — Third party provider (Amazon Mechanical Turk)
Comprehensive — MED — Parameters match most of Bellabeat products’ parameters
Current — LOW — Data is 5 years old and may not be relevant
Cited — LOW — Data collected from third party, hence unknown
Overall, the dataset is considered bad quality data and it is not recommended to produce business recommendations based on this data.
We are using Mysql for data cleaning, transformation and creating Queries and Excel for data Visualization
Import 3 files into MySQL Workbench
1) dailyActivity_merged.csv
2) sleepDay_merged.csv
3) weightLogInfo_merged.csv
Explore and observe data
Check for and treat missing or null values
Transform data — format data type.
Create queries for Visualizations.
Observe and familiarize with data
Check for null or missing values
Perform sanity check of data
-
You Can check my work of process data from dirty to clean by clicking the links below :-
Create Differnt Query tables tp perform Analysis on Excel
You can Check my queries here
-
Perform calculations Pulling statistics for analysis:
-
count — no. of rows
-
mean (average)
-
std (standard deviation)
-
min and max
-
percentiles 25%, 50%, 75%
Like Bellabeat makes smart technology designed to track, contextualize, and present personal health data to their users in a comprehensible manner. FitBit/Bellabeat Leaf wearers use this data to improve their health, so it makes sense to analyze usage to identify the healthy (and unhealthy) tendencies shown in the data. Primarily, I’ll be looking at sleep, calories, and steps/activity.
Recommended sleep per night is 7 hours or more according to the CDC
Sedentary minutes had the strongest linear relationship to how much sleep users got per night
At an R² value of roughly 0.04, it’s unclear what if any effect daily steps had on sleep
Participants spent the most time awake in bed on Sunday nights
Out of the four levels of activity, fairly active minutes seemed to have the biggest effect on how long it took to fall asleep. However, at an R² value of only 0.103, it can’t be deemed a strong determining factor
It’s unclear what if any effect total steps had on how long it took to fall asleep each night
Sleep was less frequently recorded on weekdays, particularly in the middle of the week
Overall, average calorie expenditure didn’t vary much by day of the week. The difference between the highest and lowest average was 166 calories, about the same as a small handful of almonds
Very active minutes had the strongest effect on daily caloric expenditure
Total daily steps also had a moderately strong effect on caloric expenditure
Hours slept had little to no effect on calories burned the next day; similarly, calories burned had little to no effect on how many hours were slept that same night
Between the three subgroups of daily active distances, distances traveled while very active (which FitBit calculates using the wearer’s heart rate) showed the strongest linear relationship to caloric expenditure
Average daily steps was under the recommended amount of 10,000 for every day of the week
Both the highest and lowest average occurred on the weekend
Sedentary activity, notably bad for your health, accounted for a vast majority of participants’ time
Sleep
-
On average, participants could’ve used more sleep throughout the week.
-
One way to do this might’ve been decreasing sedentary activity (by increasing the amount of time spent active).
-
For weekends specifically, reducing the amount of time spent in bed awake could’ve helped participants get more sleep.
-
Sleep was less frequently recorded on weekdays, but there were a lot of missing sleep records in general. Similarly, a quarter of the participants didn’t record any sleep data at all. Improvement in both of these areas would increase the reliability of the data.
Calories
-
Participants didn’t burn more calories on days that they worked vs. days they didn’t.
-
If users want to burn calories, they’re best off doing so by being very active and/or increasing their daily step count.
Steps/Activity
-
Participants could’ve used nudges on Sundays and Fridays to be more active.
-
Whether due to work or other reasons, the large amount of sedentary activity was a problem that seems not to have been addressed in any actionable way by participants’ FitBits.
Interrupt long periods of sedentary behavior with encouragements to be active.
Even a short walk can help offset the consequences of being sedentary for too long, offering Bellabeat Leaf wearers the opportunity to improve their sleep and > increase the amount of daily activity they undergo.
Market the Bellabeat Leaf as being comfortable even when you’re sleeping.
Though more data is necessary to say for sure, it’s possible that sleep data is less frequently recorded because wearing a watch in bed can be uncomfortable. Showcasing the Bellabeat Leaf’s comfortability might inspire users to wear theirs at night and collect more data on their sleeping habits.
Additionally, it might be useful to emphasize that the Bellabeat Leaf’s battery last six months and doesn’t require charging at night.
Promote weight positivity so users feel encouraged and comfortable inputting their weight often.
A culture of body positivity might empower Bellabeat customers to feel safe inputting their weight into a database. Regardless of if users want to lose, gain, or > maintain their weight, they have to first know where they’re starting from.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent