Runner Data Insights and Study

Posted on Oct 15, 2017
The skills the author demoed here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.


Why do some competitive long distance runners prefer to train in groups? Does data prove training with a group help improve performance? My husband, Mani thinks so – he is running his first TCS NY marathon this year.

I am a 5K runner and I prefer to train alone as it is easier to pace myself and most importantly there is no pressure what so ever. Yes, I have finished races but not to my satisfaction. My 5K pace does not show much progress. So can training with a friend or in a group actually help me? What can historic running data show me?


To help with my research I used data from Mani’s running group. The data was collected by a group of competitive runners for over a period of nine years. The group trained to run the JPMorgan Chase corporate challenge and gradually moved to other challenges. Training runs with group or ‘speed runs’ as they call it are to challenge and motivate. The group’s coach would then collect information from each runner and enter it manually into excel to yield calculations like pace, speed and to provide comparative analysis. The group also uses running apps like run-keeper or map-my-run.

Research Questions

For my analysis, I categorized the runs as ‘Speed Runs’, ‘Corporate challenge’ and ‘other races’ based on the race dates.  I selected two runners one who trained regularly and one that did not but still ran other races. With that I attempted to answer the following questions:

  1. Speed Run correlation: How do speed runs correspond to other races. Do they correlate?
  2. Average Pace: What does a one’s progress look like over the years? Has their average pace improved?

Data Insights

First to get a sense of what the pace looks over the years, I selected one runner who trains with group regularly and has been running corporate challenge for a long time and eventually ran other races.

The below graph uses plotly to trace the average pace over the years grouped by the race type.


  1. The pace was converted to a ten mile average to smoothen the lines.
  2. The Y-axis showing the pace is flipped to show an upward trend.

Runner 1: trains regularly.

Runner Data Insights and Study


The graph indicates a positive correlation between training runs and the progress in the corporate run pace. One thing I noticed was the average pace improved over the years. As the pace shown is a 10 mile average, I decided to plot another graph to see if there is a connection between mileage and pace.

Runner Data Insights and Study

Its very evident that the runner’s pace improved as he increased his mileage.

Runner 2 : did not train with the group but ran other races.

Runner Data Insights and Study

The runner showed a downward trend with respect to his pace in actual races.


Interestingly his pace got worse as he increased his mileage. There could be several factors contributing to the decline. But what stands out from the above graph is his lack of training.


Data Projections

Historical running data can be used to predict future race performances. I used Pete Riegel’s formula, t2 = t1 * (d2 / d1)1.06 to calculate the time taken to finish a distance given the 10 mile historic average. The time was converted to minutes to supplement calculations.


1.    Web scraping of web sites like strava, run keeper to derive more insights – more historic data to supplement accurate results.

2.    Projections – more projections to achieve goal using linear regression.



While there are a lot of factors both physiological and psychological, that contribute to performance in a race, I only attempted to show the correlation between training and performance. Based on the above representations of runs that show a positive correlation between training runs and actual race performance, it is safe to assume that training with a group and increasing mileage definitely supplements better performance at a race. 


NYRR - New York Road Runners

About Author

Lalith Sugavanam

Lalith holds a Masters degree in computer applications from Bharathidasan University, India. She loves to program and has more recently progressed into a fascination with extracting meaning from data. She's completed a 12-week Data Science course at NYCDS.
View all posts by Lalith Sugavanam >

Related Articles

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI