FAQ

NEO is an autonomous ML agent that automates most stages of the pipeline, from data preparation to deployment.

Workflow:

1. Describe your ML task in natural language
2. Provide data (upload, URL, or cloud)
3. NEO analyzes data and selects models
4. Receive production-ready artifacts with documentation

Example task:

Build a customer churn prediction model using customer_data.csv. 
Optimize for recall since missing churners is costly.

NEO handles preprocessing, feature engineering, training, evaluation, and artifact generation automatically.

NEO supports multiple ML domains:

• Tabular ML – Classification, regression, clustering, time series
• Computer vision – Image classification, object detection, OCR
• NLP – Text classification, sentiment analysis, NER, summarization
• Audio and speech – Speech recognition, audio classification
• LLM fine-tuning – Instruction tuning, LoRA, domain adaptation
• Anomaly detection – Outlier detection, fraud detection

No. NEO is designed for all skill levels.

The key is clear goal description, not prior ML knowledge.

Tip: Start with a small sample, then scale.

Approach:

1. Platform – Use cloud storage (S3, Google Cloud Storage, Azure Blob Storage)
2. Convert to Parquet – Faster processing
3. Test first – Use 10% sample

File limits:

• Platform upload: 50MB per file
• Platform cloud storage: unlimited
• VS Code: unlimited local files

Yes. Automatic detection and imputation:

Platform mode: Quick results, no setup, collaborative testing

VS Code extension: Edit code, work with large local files, full IDE features, version control

Include:

1. Goal – What to predict or classify
2. Data – Files, size, key columns
3. Metrics – How to measure success
4. Context – Business relevance

Example comparison:

Map metrics to business goals:

• Minimize false positives → precision
• Catch all fraud → recall
• Balance speed and accuracy → F1-score

Platform: Cloud encrypted, deletion on request, no sharing

VS Code: Local files never leave machine, secure cloud access via credentials, full control

Yes, NEO provides:

• Preprocessing and modeling code
• Step-by-step notebooks
• Deployment scripts
• Documentation and methodology

Improvement steps:

1. Improve data quality and features
2. Adjust metrics and constraints
3. Provide domain knowledge
4. Request specific approaches (ensembles, deep learning)

Focus on practical business impact, not perfect accuracy.