You will get Time Series Anomaly Detection
Project details
Detect anomalies in your time series data using a powerful hybrid model that combines a PyTorch Autoencoder with Rolling Z-Score. I prepare your dataset, train the model, and deliver clear anomaly charts and detailed insights so you can understand unusual events and make data-driven decisions.
Machine Learning Tools
Python, PyTorchWhat's included $100
These options are included with the project scope.
$100
- Delivery Time 2 days
- Number of Revisions 1
- Number of Model Variations 1
- Number of Scenarios 1
- Number of Graphs/Charts 2
- Model Validation/Testing
- Model Documentation
Optional add-ons
You can add these on the next page.
Additional Scenario
+$20
Source Code
+$20Frequently asked questions
About Guilherme
ML Engineer
Suzano, Brazil - 12:56 pm local time
🚀 I build, train and deploy intelligent systems that transform data into real business impact.
Hi, I’m Guilherme — Specialized in Machine Learning, Deep Learning, and end-to-end AI automation.
🧠 I specialize in:
• Machine Learning model development & optimization
• Deep Learning with TensorFlow, PyTorch & Keras
• Computer Vision, NLP & Data Preprocessing pipelines
• AI-powered automation & predictive analytics
⚙️ My workflow:
I analyze your problem, design a tailored AI solution, and provide clear progress updates —
so you always understand the results and their real-world impact.
Every project I build is production-ready, from training to deployment.
✨ Let’s bring your vision to life with precision, clarity, and cutting-edge technology.
by Guilherme | ML Engineer
Steps for completing your project
After purchasing the project, send requirements so Guilherme can start the project.
Delivery time starts when Guilherme receives requirements from you.
Guilherme works on your project following the steps below.
Revisions may occur after the delivery date.
Upload your time series dataset (CSV/Excel).
Please send the dataset with timestamps and the signal you want analyzed. You may also include known anomalies or notes about expected patterns.
Data cleaning and preparation.
I will load, clean, scale, and prepare your data for anomaly detection, ensuring the time series is ready for the hybrid model.