Robyn

Robyn

Meta
TimesFM-3

TimesFM-3

Google
+
+

Related Products

  • RaimaDB
    12 Ratings
    Visit Website
  • TrafficGuard
    89 Ratings
    Visit Website
  • IUX
    930 Ratings
    Visit Website
  • 800.com
    2,370 Ratings
    Visit Website
  • Evertune
    1 Rating
    Visit Website
  • MikMak
    85 Ratings
    Visit Website
  • Superfiliate
    38 Ratings
    Visit Website
  • Vantage
    14,866 Ratings
    Visit Website
  • Yeastar P-Series PBX System
    116 Ratings
    Visit Website
  • Gemini Enterprise Agent Platform
    999 Ratings
    Visit Website

About

Robyn is an open source, experimental Marketing Mix Modeling (MMM) package developed by Meta’s Marketing Science team. It’s designed to help advertisers and analysts build rigorous, data-driven models that quantify how different marketing channels contribute to business outcomes (like sales, conversions, or other KPIs) in a privacy-safe, aggregated way. Rather than relying on user-level tracking, Robyn analyzes historical time-series data, combining marketing spend or reach data (ads, promotions, organic efforts, etc.) with outcome metrics, to estimate incremental impact, saturation effects, and carry-over (adstock) dynamics. Under the hood, Robyn blends classical statistical methods with modern machine learning and optimization; it uses ridge regression (to regularize against multicollinearity in many-channel models), time-series decomposition to isolate trend and seasonality, and a multi-objective evolutionary algorithm.

About

TimesFM-3 is a state-of-the-art time series foundation model designed for highly accurate multivariate forecasting in a single forward pass. The 330 million parameter model is pre-trained on a real-world and synthetic time-series corpus comprising more than 1 trillion time points, building on the efficiency and zero-shot generalization of earlier TimesFM models. It can jointly predict multiple coevolving time series and capture dependencies that improve accuracy without task-specific fine-tuning. The model supports multiple targets with point and quantile forecasts, past covariates that are known only historically, and past-future dynamic covariates such as planned promotions, holidays, or weather forecasts. TimesFM-3 uses a decoder-only transformer architecture, processes contiguous data in patches of 32 time steps, and applies alternating causal temporal attention and full variate attention to combine patterns across time and related series.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

Marketing teams, data scientists, and analysts interested in a solution to measure real incremental impact, attribute performance across channels, and optimize budget allocation in a transparent, privacy-compliant way

Audience

Data scientists, researchers, and developers wanting to forecast multiple related time series and incorporate historical and known future signals

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

Free
Free Version
Free Trial

Pricing

No information available.
Free Version
Free Trial

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Meta
Founded: 2004
United States
facebookexperimental.github.io/Robyn/

Company Information

Google
Founded: 1998
United States
research.google/blog/timesfm-3-a-zero-shot-foundation-model-for-multivariate-forecasting/

Alternatives

Alternatives

CodeQwen

CodeQwen

Alibaba
Kimi K2

Kimi K2

Moonshot AI
Qwen-7B

Qwen-7B

Alibaba

Categories

Categories

Integrations

Facebook
Facebook Ads
Instagram Ads
Meta Ads
Meta Pixel

Integrations

Facebook
Facebook Ads
Instagram Ads
Meta Ads
Meta Pixel
Claim Robyn and update features and information
Claim Robyn and update features and information
Claim TimesFM-3 and update features and information
Claim TimesFM-3 and update features and information