OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Mlgb

Mlgb is a Python library of deep-learning models for click-through-rate prediction and recommender systems, supporting TensorFlow and PyTorch. It groups ranking, matching and multitask-learning models behind a configurable model interface.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Mlgb — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Mlgb when you want a Python model library for experimentation with CTR prediction or recommendation tasks and can supply your own features and pipeline.

Who it is for

  • Machine-learning practitioners prototyping CTR-prediction models.
  • Recommendation-system developers exploring ranking and matching architectures.
  • Researchers comparing documented model choices across TensorFlow and PyTorch.

Documented uses

  • Select a library model for a ranking, matching or multitask-learning task.
  • Configure a model for binary, regression or multiclass prediction.
  • Explore model parameters and compare CTR-prediction or recommendation architectures.
Before you choose

Requirements & limits

The repository is public and specifies the Apache-2.0 license. The README documents installation through PyPI or Conda.

  • The library supports TensorFlow and PyTorch, with TensorFlow as the documented default.
  • Model selection includes ranking, matching and multitask-learning aims, and binary, regression and multiclass tasks.
  • Feature names are required; embedded features need vocabulary sizes and custom embedding dimensions.
  • The documented installation paths are PyPI and Conda; the README does not provide a complete data-to-deployment workflow.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Mlgb and inspect model options

Install the library and review its documented model interface and parameters.

Before you start

  • Python environment with pip or Conda available.

Steps

  1. Install with the command below or conda install conda-forge::mlgb.

    Documented command
    pip install --upgrade mlgb

  2. Import the package with import mlgb.

  3. Use help(mlgb.get_model) to inspect the model-selection parameters.

  4. Use mlgb.get_model_help(model_name='LR', lang='tf') to inspect an example model's parameters.

Expected outcome

The library is installed and its documented model and parameter interfaces can be consulted.

Guide limitations

  • This setup and inspection flow does not cover preparing data, training a model, or deploying a prediction service.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
6 November 2026
Original website title
UlionTse/mlgb · Official homepage title · retained in its source language
How we review sourcesSuggest a correction