Freelancer logo
Log In Sign Up
Post a Project

EXPLORE

Copywriting Excel Graphic Design Logo Design Python
Profile cover photo
User Avatar

Bram A.

@kazenesia

0.0
0

0.0

0.0

0%

Data Analyst & Machine Learning Specialist

$15 USD / Hour

・

Flag of

Indonesia (12:12 PM)

・

Joined on October 8, 2025

$15 USD / Hour

・

Are you looking to turn your data into real business results? I help businesses analyze data, predict future trends, and optimize revenue using data analytics and machine learning. Here’s how I can help you: ✔ Sales forecasting to predict future revenue ✔ Customer churn analysis to reduce customer loss ✔ Pricing optimization to maximize profit ✔ Data analysis & visualization for better decision-making I have built multiple end-to-end data projects including: * E-commerce Churn Prediction & CLV Analysis * Dynamic Pricing Optimization * Sales Forecasting Models * Supply Chain Optimization What makes me different: * I focus on business impact, not just technical output * I explain insights in a clear and simple way * I deliver actionable recommendations Let’s discuss your project and find the best solution for your data.

Verifications

Freelancer Python Developers Indonesia
See all Python Developers in Indonesia

Portfolio

Portfolio

13847036
A twelve‑module analytics platform analyzed 50,000 learners across six countries to predict dropout, model engagement, and simulate interventions, finding that a composite Student Engagement Index (SEI)—built from Time Commitment, Academic Quality, Platform Activity, and Social Learning—is the strongest predictor of dropout (behavior beats demographics), an ensemble of XGBoost/LightGBM/CatBoost achieved 99.72% AUC and F1 = 0.9522, risk tiers were highly precise (Low Risk = 0.0% dropout; Critical Risk = 99.7%), multi‑dimensional “Full Interventions” produced the largest simulated risk reductions, and correcting a data‑leakage issue (attendance proxy) was essential to preserve model integrity.

AI Student Success Intelligence

AI Student Success Intelligence

13846999
An end-to-end pipeline built on Google Colab ingests and cleans market feeds, engineers 43 signals (momentum, volatility, liquidity), detects market regimes (Bull, Bear, High Volatility) via KMeans/HMM/GMM, models 24‑hour alpha with a Random Forest, detects anomalies with Isolation Forest and Autoencoders, and backtests strategies versus benchmarks like BTC buy‑and‑hold; key findings: the SELL signal is highly precise (only 5.14% of SELLs rose next day), the Random Forest achieved 0.7714 ROC‑AUC, anomalies were more bullish (36.87% up vs 25.49% for normal observations), SHAP shows price‑level context and regime probabilities dominate feature importance, and the model favors low‑volatility, defensive assets (e.g., gold‑pegged tokens) while a passive market‑cap approach briefly outperformed during a short recovery week.

Crypto Market Intelligence

Crypto Market Intelligence

13846851
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.

Product Success & Strategic Market

Product Success & Strategic Market

13846748
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.

Global Smartphone Sales Strategy

Global Smartphone Sales Strategy

13846715
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. Summary of Findings 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. Operational Impact: The AI-driven approach successfully identified complex patterns and statistical outliers at a scale unattainable by manual processes, providing a structured roadmap for improved governance and financial oversight.

AI-Driven Sales Anomaly Detection

AI-Driven Sales Anomaly Detection

13845657
Developed a dynamic pricing system to adjust prices in real-time based on market demand, competition, and customer behavior. Conducted market research, built pricing algorithms, and integrated them into the platform. Used data analysis to identify optimal pricing strategies and monitored their impact on key metrics.

Dynamic Pricing for an E-commerce

Dynamic Pricing for an E-commerce

13847036
A twelve‑module analytics platform analyzed 50,000 learners across six countries to predict dropout, model engagement, and simulate interventions, finding that a composite Student Engagement Index (SEI)—built from Time Commitment, Academic Quality, Platform Activity, and Social Learning—is the strongest predictor of dropout (behavior beats demographics), an ensemble of XGBoost/LightGBM/CatBoost achieved 99.72% AUC and F1 = 0.9522, risk tiers were highly precise (Low Risk = 0.0% dropout; Critical Risk = 99.7%), multi‑dimensional “Full Interventions” produced the largest simulated risk reductions, and correcting a data‑leakage issue (attendance proxy) was essential to preserve model integrity.

AI Student Success Intelligence

AI Student Success Intelligence

13846999
An end-to-end pipeline built on Google Colab ingests and cleans market feeds, engineers 43 signals (momentum, volatility, liquidity), detects market regimes (Bull, Bear, High Volatility) via KMeans/HMM/GMM, models 24‑hour alpha with a Random Forest, detects anomalies with Isolation Forest and Autoencoders, and backtests strategies versus benchmarks like BTC buy‑and‑hold; key findings: the SELL signal is highly precise (only 5.14% of SELLs rose next day), the Random Forest achieved 0.7714 ROC‑AUC, anomalies were more bullish (36.87% up vs 25.49% for normal observations), SHAP shows price‑level context and regime probabilities dominate feature importance, and the model favors low‑volatility, defensive assets (e.g., gold‑pegged tokens) while a passive market‑cap approach briefly outperformed during a short recovery week.

Crypto Market Intelligence

Crypto Market Intelligence

13846851
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.

Product Success & Strategic Market

Product Success & Strategic Market

13846748
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.

Global Smartphone Sales Strategy

Global Smartphone Sales Strategy

13846715
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. Summary of Findings 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. Operational Impact: The AI-driven approach successfully identified complex patterns and statistical outliers at a scale unattainable by manual processes, providing a structured roadmap for improved governance and financial oversight.

AI-Driven Sales Anomaly Detection

AI-Driven Sales Anomaly Detection

13845657
Developed a dynamic pricing system to adjust prices in real-time based on market demand, competition, and customer behavior. Conducted market research, built pricing algorithms, and integrated them into the platform. Used data analysis to identify optimal pricing strategies and monitored their impact on key metrics.

Dynamic Pricing for an E-commerce

Dynamic Pricing for an E-commerce

Reviews
0 Reviews

No reviews to see here!

Education

Universitas Muhammadiyah Sidoarjo

2020 - 2026

•

6 years

BA Computer Science

Flag of

Indonesia

2020 - 2026

•

6 years

Freelancer logo US (International) / English
Help & Support

Freelancer

Categories Projects Contests Freelancers Enterprise Innovation Challenges AI Development Membership Preferred Freelancer Program Project Management Local Jobs Photo Anywhere Showcase API for Developers Get Verified

About

About us How it Works Security Investor Sitemap Stories News Team Awards Press Releases Careers

Terms

Privacy Policy Terms and Conditions Copyright Policy Code of Conduct Fees and Charges

Partners

Escrow.com Loadshift Warrior Forum

Apps

Apple App Store logoGoogle Play logo

Registered Users

Total Jobs Posted

Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)

Copyright © 2026 Freelancer Technology Pty Limited (ACN 142 189 759)