Build-My-ML

BuildMyML – An Intelligent and Explainable AutoML Project Design is an AI-powered framework that simplifies the planning and design of machine learning projects. It allows users to describe their project idea in natural language and helps transform it into a structured ML project blueprint. The system combines Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to provide context-aware recommendations for problem formulation, preprocessing, feature engineering, model selection, evaluation metrics, and ML workflow design. A curated machine learning knowledge base is processed through document ingestion, text chunking, embedding generation, and semantic retrieval using Supabase and pgvector, while the Gemini API is used for language understanding and recommendation generation. The proposed system aims to reduce the manual research and expertise required for ML project planning and provide users with a more systematic, explainable, and accessible way to design machine learning projects.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-10-08
DOI
https://doi.org/10.5281/zenodo.23231752
Primary Topic
Artificial Intelligence Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Build-My-ML

Aayush N Nataraj, Hima Parvathi A Anand, B Rishitha Boppana, Harshita R Ravindra
Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence Applications
article

Build-My-ML

Aayush N Nataraj, Hima Parvathi A Anand, B Rishitha Boppana, Harshita R Ravindra
article en

Abstract

BuildMyML – An Intelligent and Explainable AutoML Project Design is an AI-powered framework that simplifies the planning and design of machine learning projects. It allows users to describe their project idea in natural language and helps transform it into a structured ML project blueprint. The system combines Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to provide context-aware recommendations for problem formulation, preprocessing, feature engineering, model selection, evaluation metrics, and ML workflow design. A curated machine learning knowledge base is processed through document ingestion, text chunking, embedding generation, and semantic retrieval using Supabase and pgvector, while the Gemini API is used for language understanding and recommendation generation. The proposed system aims to reduce the manual research and expertise required for ML project planning and provide users with a more systematic, explainable, and accessible way to design machine learning projects.

Zenodo (CERN European Organization for Nuclear Research)
Openalex Percentile: Top 12%
Artificial Intelligence Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.