Freelancers using scikit-learnFreelancers using scikit-learn
ProjectsPeople
Widada Widada's avatar
Widada Widada
Yogyakarta, Indonesia
Expert Backend Developer & Data Scraper
$25k+
Earned
2x
Hired
5.0
Rating
31
Followers
Expert Backend Developer & Data Scraper
Cover image for Fullstack Developer & Data Engineer
Fullstack Developer & Data Engineer
1
19
Cover image for Fullstack Development: Build Scrapers and AI Integration
Fullstack Development: Build Scrapers and AI Integration
1
10
Cover image for N8N Automation for Zillow
N8N Automation for Zillow
1
8
Cover image for Automated Multilingual Property Description Generator
Automated Multilingual Property Description Generator
1
10
scikit-learn(1)
kaze nesia's avatar
kaze nesia
Surabaya, Indonesia
Full-Stack Data Specialist | Automation & Predictive
New to Contra
Full-Stack Data Specialist | Automation & Predictive
Cover image for Advanced Crypto Market Signal Engine with High Precision SELL
Crypto Market Intelligence & Alpha Signal Engine An end-to-end Colab pipeline ingests market feeds, engineers 43 signals, detects regimes (KMeans/HMM/GMM), models 24‑hour alpha with a Random Forest (ROC‑AUC 0.7714), flags anomalies (Isolation Forest/Autoencoders), and backtests strategies; key findings: the SELL signal is highly precise (only 5.14% of SELLs rose next day), anomalies are often bullish (36.87% up vs 25.49% normal), price‑level context and regime probabilities drive predictions, and the model favors low‑volatility, defensive assets during downturns.
0
106
Cover image for Global Retail Intelligence System: Product
Global Retail Intelligence System: Product Success Prediction and Strategic Market Analysis A multi-stage ML pipeline analyzed 44,888 Adidas SKUs using XGBoost and Random Forest to predict product success, demand trajectories, and stockout risk, finding that subcategory is the dominant success driver (~6× more explanatory than price, discount, or geography), the Success Classifier reached 94.3% accuracy and the Stockout Risk model 0.99 ROC‑AUC, 42.5% of products carry markdowns with deep discounts (≥30%) often eroding margins, 323 high-performing SKUs are under‑distributed and present near‑term expansion opportunities, the Budget tier outperforms Premium/Luxury in conversion to high performers, and 653 SKUs were flagged as high demand with elevated stockout risk requiring urgent replenishment.
0
78
Cover image for AI-Driven Global Smartphone Sales Strategy
AI-Driven Global Smartphone Sales Strategy Optimizer An end-to-end ML project used four years of global sales data and 132,000+ simulations to optimize pricing across 52 countries, identifying the exact product, channel, and price to maximize profit. Key findings: the “Discount Myth”—discounting has almost no effect on volume but erodes margins; switching from blanket 20% discounts to AI‑optimized pricing yields a 15.1% revenue gain (about $73,993 preserved per simulation). The B2B channel is optimal in 90% of markets. The production XGBoost model achieves 99.73% accuracy, and ultra‑premium products (notably the Samsung Neo QLED 8K) consistently generate the highest revenue.
0
88
Cover image for AI-Driven Sales Anomaly Detection: Executive
AI-Driven Sales Anomaly Detection: Executive Intelligence Report A machine learning investigation analyzing 2.8 million retail transactions across seven countries. The project utilizes a multi-model ensemble—including Isolation Forest, Local Outlier Factor (LOF), One-Class SVM, and LSTM Autoencoders—to identify revenue leakage, pricing inconsistencies, and operational risks within global retail operations. Critical Anomalies: Four high-priority transactions were unanimously flagged by all four independent machine learning models, representing the most significant and actionable risks identified in the dataset. Systemic Vulnerabilities: The analysis pinpointed specific weaknesses in discount authorization processes and pricing chain integrity, particularly within the UAE market.
0
89
scikit-learn(5)
Gary Ernstzen's avatar
Gary Ernstzen
Cape Town, South Africa
AI Workflow Automation for SMEs, Boost Productivity & Profit
New to Contra
AI Workflow Automation for SMEs, Boost Productivity & Profit
Cover image for Predictive Maintenance & AI Insights We created a bespoke AI...
Predictive Maintenance & AI Insights We created a bespoke AI-driven platform to revolutionize customer support for a prominent e-commerce enterprise. Confronted with a surge of inquiries and operational challenges, the client sought a scalable solution. Our team deployed a system leveraging machine learning models that automates ticket management, classifies inquiries, and delivers real-time predictive insights. This implementation has greatly diminished manual workload, enhanced response times, and boosted customer satisfaction through a more efficient and tailored support experience.
0
7
Cover image for Self-Hosted AI Assistant Platform We created an innovative s...
Self-Hosted AI Assistant Platform We created an innovative solution by combining n8n and Ollama, facilitating seamless, local interactions with Large Language Models (LLMs). This self-hosted platform empowers businesses to operate AI models securely and privately on their own infrastructure, thereby removing the necessity for costly cloud services. With real-time data processing, economical model utilization, and improved AI response times, this platform is perfect for enterprises aiming to harness AI for experimentation, learning, and prototyping without depending on external cloud services. The solution not only ensures security and privacy but is also scalable to accommodate increasing user demands and expanding AI capabilities.
0
7
Cover image for Smart Booking & Scheduling System We developed a customized ...
Smart Booking & Scheduling System We developed a customized platform that connects tutors and alumni with students through the integration of Wix Bookings. This platform simplifies the booking and scheduling process, offering both flexibility and user-friendliness. Tutors and alumni are able to manage their availability, create profiles, and communicate efficiently with students, while students can effortlessly book sessions and share feedback. The outcome is a scalable solution that caters to the needs of individual tutors as well as larger educational institutions.
0
6
Cover image for AI-Driven Customer Support Efficiency We created a tailored ...
AI-Driven Customer Support Efficiency We created a tailored AI-driven platform designed to revolutionize customer support for a prominent e-commerce company. Confronted with a surge in inquiries and operational hurdles, the client sought a scalable solution. Our team deployed a system utilizing machine learning models to automate ticket management, classify inquiries, and deliver real-time predictive insights. This implementation has notably diminished manual workload, enhanced response times, and boosted customer satisfaction by offering a more efficient and personalized support experience.
0
6
scikit-learn(4)