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
Title : Loan Approval Prediction System
Description : Developed a machine learning-based Loan Approval Prediction System that helps financial institutions assess loan eligibility using applicant information such as income, education, employment status, loan amount, credit history, and marital status. The project includes data preprocessing, feature engineering, model training, and an interactive web interface for real-time predictions. The solution enables faster and more consistent loan approval decisions through data-driven analysis.
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
Most travel apps feel like impersonal search directories that you can clearly tell were made for your typical traveler - you know, the one that's going on vacation and leaving all worries behind?
But that's not us. We are freelancers, which means we get the freedom to travel, but also means client work also gets the freedom to travel alongside us. What a lucky bastard!!
Well, this app reimagines the digital nomad journey in the city I know best, Lisbon, through the lens of a local friend. It blends a work mode with vetted co-working spaces with a gamified travel scrapbook, ensuring you experience the authentic culture of the city while building a physical visual log of your stay - no matter the budget you're on!
🛠️ The Tech & Design Workflow
To get to this final working prototype, I utilized a connected pipeline across Figma’s advanced tool ecosystem:
⭐️ Figma Design: used as the initial creative sandbox to establish the visual identity, typography, and layout foundations.
⭐️ Figma Make: transformed my static design inspiration into a living, interactive, code-backed prototype with several back-and-forth iterations.
⭐️ Figma Weave: used to create a custom filter to add to user's photos, using its node asset pipeline.
📊 Architecture & Scalability
Instead of hardcoding a long database, all the co-working spaces and travel quests are stored in an external Google Sheet exported as a live, public CSV. This allows for instant, real-time data updates without redeploying code, making the app entirely scalable at any time.
Also, every recommendation and description for the co-working spaces was written by me from personal, first-hand visits. The travel quests are a blend of personal recommendations and some of my bucket-list items - maybe you'll cross them off sooner than me!
💰 Monetization & The Organic Growth Loop
To keep the platform 100% free for users, the plan is to develop affiliate agreements with co-working spaces and paid local experience hosts, earning small commissions per booking.
On the other hand, completing quests rewards users with points. And while currently displayed as a "coming soon" placeholder, the road map plans to allow users to redeem these points for real-life gift cards to drive long-term user retention.
Lastly, there's some built-in word of mouth, since the scrapbook features a prominent share button on your custom-filtered photos. This turns users into organic brand ambassadors when they share their custom-doodled memories with family back home or on social media.
Figma Design project: https://www.figma.com/community/file/1649623170040464186
Figma Make project: https://www.figma.com/community/file/1649623797184817979
Working app: https://tempo-slush-47265679.figma.site/
Great job Silvia 😍 🔥 🙌
Hi everyone! 👋
For #ConfigMakeathon, I built Fortune Crumbs 🥠
Lately I've noticed that whenever I'm stuck on something (either for work, life, a random decision) I end up opening an AI Model looking for direction.
The funny thing is that sometimes a simple question turns into a very long conversation. And then sometimes becomes often
That got me thinking: what if... the opposite existed?
Fortune Crumbs is a tiny experience inspired by fortune cookies. You choose a path (Life or Work), type what's on your mind, and crack open a cookie to reveal a fortune.
Not a perfect answer. Not a detailed analysis.
Just a small nudge, a different perspective, or maybe a reminder of something you already knew. Or maybe, just a simple nonsense helping you to move on.
I liked the idea of creating something a little more playful and ephemeral. An experience that lasts a few seconds, gives you something to think about, and then disappears. Something to have fun, validate, annoyed, to be shared, to be kept. And that idea got translated, tested, edited and launch with Figma Make.
Something with little to no expectations but a bit of fun.
In a world where we can ask AI almost anything, it felt fun to build something that responds with just one thought.
Give it a try: https://fortunecrumbs.figma.site
If you enjoy it, I'd love to hear what fortune you got ✨
The contrast with how we normally use AI is what makes this land. Everything is optimized for more information, more analysis, more context. Building something that deliberately gives you less and just one thought is a genuinely different design decision. Did the fortunes change how you'd expect people to use it?
I Take AI Slop and Turn It Into Product
At SanganakHQ, I've done this at least half a dozen times now. Same story every time.
Founder builds with Claude, Codex, Bolt, Replit, Lovable, v0. And it works. Real users, real payments, real data.
But under the hood? 50K, 100K+ lines of AI-generated code glued together. Functions duplicated dozens of times. Auth mixed into UI. Hardcoded secrets. No tests. Fix one bug, three more appear.
It works the way a house of cards works.
Then they message me: "We're scaling. Can you make this production-ready?"
So I audit every line. Separate what's solid (usually 20%) from what needs to be rearchitected. Build a day-by-day migration plan with exact pricing. Move it to a real stack: Next.js, Supabase, Vercel, proper auth, proper RLS, proper CI/CD.
The irony: the AI features are usually the cleanest part. The mess is everything around it. Business logic, payment flows, membership tiers. The stuff AI generated fast but never thought through.
Smart founders, solid ideas, AI got them to a working product. But "working" and "production-grade" are two very different things.
If your app runs on AI-generated code and you're about to scale, get it audited before you find out the hard way.
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?