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
Smart Delivery Time Predictor is a machine learning system for estimating food delivery times using historical delivery information and contextual factors such as traffic and weather.
I built the data-processing and modelling workflow including exploratory data analysis, preprocessing, datetime feature extraction, categorical encoding, feature selection using SelectKBest, and hyperparameter optimization with GridSearchCV.
I evaluated multiple regression approaches including Linear Regression, Decision Tree, Bagging, Random Forest, Elastic Net, LightGBM, and XGBoost. LightGBM achieved the strongest reported performance in the project with an R² score of 0.80.
The project also includes a command-line prediction interface that allows users to provide delivery parameters and receive an estimated delivery-time category.
This demonstrates practical experience taking a machine-learning problem from raw data and feature engineering through model comparison, optimization, evaluation, and usable prediction.
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
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
Silpo is a big chain of modern supermarkets in Ukraine.
It is famous for its innovative approaches and next-level marketing.
I'm taking part in a challenge to develop a custom autonomous AI Agent for Silpo that will help Silpo's customers make grocery shopping easier.
In the image below, you can see a visualization of how this agent gonna work.
I'd love to hear: what would you like for such an agent to be capable of doing?
Wow, love it Siplo to next level!!!!
Three years ago, we built a service provider booking app (plumbers, carpenters, electricians) from scratch, fully custom code. Took close to 4 months to get live.
Today, with AI tools like Claude and ChatGPT in the workflow, I think a comparable MVP could realistically ship in 4-6 weeks. The boilerplate and repetitive work compress fast, matching logic and payment edge cases still need real engineering judgment.
If you had to rebuild something similar today, what timeline would you expect?
Four to six weeks feels realistic for a focused MVP now. The acceleration is real, but matching rules and payment edge cases are still where the product needs careful engineering.
The Impossible Prediction 🌌
For the Flora Museum Challenge, I reimagined the Met Museum’s Automaton Clock in the Form of Urania, Muse of Astronomy by Paullus Schiller (ca. 1620–30) as the center of a fictional scientific mystery.
The story begins in a 17th-century workshop, where Schiller is building Urania, a mechanical representation of the heavens. Once completed, the automaton comes alive: its gears turn, the celestial sphere rotates, and Urania moves as she tracks the heavens.
But something unexpected happens. One of the gears begins moving differently from the others. Schiller initially believes it is simply a mechanical flaw, but the unusual movement continues with strange precision.
The story then jumps forward 400 years. Modern researchers rediscover Urania and analyze the mysterious gear using contemporary astronomical data. What first appears to be an error turns out to correspond to a precise location in the night sky — something that could not have been known in Schiller’s time.
The researchers are left with an impossible question: How could a 17th-century machine contain an astronomical prediction about something discovered centuries later?
Using Flora, I developed this idea into a five-part visual narrative — The Creation, The Awakening, The Anomaly, 400 Years Later, and The Revelation — and turned it into a short cinematic demo.
The project explores how a real historical object can inspire an entirely new fictional world while preserving the character, craftsmanship, and astronomical identity of the original artifact.
Turning Urania into the center of a scientific mystery is such a strong narrative leap. The automaton clock already feels uncanny, and this concept pushes that quality beautifully.