The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Project: Velocity SaaS – Revenue Turnaround Analysis
Type: Independent portfolio project
Dataset: Synthetic B2B SaaS, 2,000 accounts / 2.2M rows, benchmarked against ProfitWell/OpenView
What I did:
MRR waterfall analysis, churn segmentation by plan/industry/channel
Usage decay / silent churn risk modeling
Logistic regression churn predictor: 98% recall, 70% precision, 0.82 F1
Built executive Looker Studio dashboard + Streamlit churn predictor
Outcome: $411K silent MRR at risk identified, CS-ready prioritized account list
Stack: SQL, DuckDB, Python, Pandas, Scikit-learn, Looker Studio, Streamlit
Live app: velocity-saas-churn-predictor.streamlit.app
Repo: github.com/SURAJRAJPUT2006
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
interesting project - there is something to take note of for effective solutions👏
I've been watching Formula 1 since 2014. Through the Mercedes era, the 2021 title fight that broke my heart and rebuilt it, and the Sunday-afternoon alarms for flyaway races, F1 has been a constant for me for over a decade.
So I finally built the thing I always wanted to exist: a real-time F1 race dashboard that doesn't just show what's happening but predicts what's about to.
🏎️ What it does:
A live track map with every car moving in real time, built from real GPS data.
Live timing, tires, gaps, and pit stops.
And the part I'm most proud of: AI predictions for tire life, pit windows, safety-car risk, and where each car will actually finish
The honest results (because numbers should mean something):
Its finishing-position guess is on average within ~2 places of where a car really ends up. So if it says "P5," reality is usually P3–P7.
It gets about 3 in 4 of its podium calls right while the race is still running.
For safety cars: when it says there's roughly a 1-in-8 chance of one soon, that's about how often one actually appears, i.e., the percentages are honest, not vibes.
What I learned the hard way: in a sport this strategic, the live running order is already a brutally good predictor. Beating it isn't about more data; it's about modeling the chaos (safety cars, rain, and DNFs). That reframing was the whole project.
Built with Python, FastAPI, React, and a Monte Carlo simulation engine. Every predicted number is labelled so it's never confused with real telemetry.
From fan to builder, easily the most fun I've had with a side project. 🏁
Repo + write-up in the comments. Would love feedback from other F1 + data folks.
Designed a modern SaaS landing page for Sync – AI Search Analytics for Marketing Teams.
Clean, vibrant UI with bold hero section, clear value proposition, smart CTAs, and sleek visual hierarchy focused on AI-powered search analytics and marketing insights.
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
MagicPath
The canvas is infinite, and exploration is becoming the workflow. How are you using MagicPath?
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?
