AmirhosseinHonardoust/AI-Assistant-Satisfaction-Prediction-Engine
A complete machine-learning system that predicts AI assistant user satisfaction using behavioral signals such as device, usage category, time features, session metrics, and model metadata. Includes full ML pipeline, SHAP explainability, evaluation suite, and an interactive Streamlit analytics dashboard.
This tool helps product managers and UX researchers understand why users are satisfied or dissatisfied with AI assistants. By analyzing behavioral data like device, usage category, session length, and the AI model used, it predicts user satisfaction ratings (1-5). You get an interpretable model that pinpoints which factors drive user happiness or frustration, enabling targeted improvements to the AI product.
Use this if you need to identify key behavioral patterns and product features that influence user satisfaction with your AI assistant and want clear, actionable insights.
Not ideal if you're looking for a simple survey analysis tool without integrating complex behavioral data or if your AI product doesn't collect detailed usage metrics.
Stars
20
Forks
—
Language
Python
License
MIT
Category
Last pushed
Dec 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AmirhosseinHonardoust/AI-Assistant-Satisfaction-Prediction-Engine"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sohds/P4DS_gaeun_allocation
2023-2 '파이썬을이용한데이터사이언스' 기말 팀 프로젝트 | 서울여자대학교 총동문회 주관 카페 '가은'의 운영효율화 전략을 위한 데이터 분석 및 머신러닝 모델 설계 |...
yamanalab/ec-darkpattern
[IEEE BigData 2022] Dark patterns in e-commerce: a dataset and its baseline evaluations
evansdoe/online_retail
The goal of this project is to build an unsupervised machine learning model that predicts...
Super-Chain/AI-Marketer
Analyze your marketing data by AI & ML algorithms without a single-line of code.
station-10/awesome-marketing-machine-learning
A curated list of awesome machine learning libraries for marketing, including media mix models,...