Autobox

Autobox

Automatic Forecasting Systems
TimesFM-3

TimesFM-3

Google
Autobox TimesFM-3

Related Products

  • Martus
    4.7 out of 5 stars 187 Ratings
    Visit Website for Martus
  • SKU Science
    4.6 out of 5 stars 16 Ratings
    Visit Website for SKU Science
  • Bridgit
    4.7 out of 5 stars 80 Ratings
    Visit Website for Bridgit
  • Kantata
    4.2 out of 5 stars 2,344 Ratings
    Visit Website for Kantata
  • Runn
    4.8 out of 5 stars 37 Ratings
    Visit Website for Runn
  • Banker's Dashboard
    4.8 out of 5 stars 6 Ratings
    Visit Website for Banker's Dashboard
  • Premier Construction Software
    4.7 out of 5 stars 409 Ratings
    Visit Website for Premier Construction Software
  • EazyStock
    4.4 out of 5 stars 65 Ratings
    Visit Website for EazyStock
  • ZenTreasury
    4.9 out of 5 stars 9 Ratings
    Visit Website for ZenTreasury
  • Project Insight
    4.5 out of 5 stars 122 Ratings
    Visit Website for Project Insight
Autobox:

About

Autobox is simply the easiest way to forecast. Designed with both the novice and expert forecaster in mind you can load your data and forecast like a Pro. No matter what method you currently use to forecast, Autobox will improve your ability to forecast accurately. Autobox won the prestigious “best-dedicated forecasting program” in the Principles of Forecasting textbook and is now a website. AFS’s unique approach doesn’t try to shoehorn the data into a model or a limited number of models, allowing Autobox to combine, history and causal are in an optimal way incorporating when needed level shifts, local time trends, pulses, and seasonal pulses. Autobox discovers new causal variables by gleaning patterns from historical forecast errors and outliers identified by the Autobox engine! Many cases result in causal variables you may not have even known existed. i.e. promotions, holidays, day of the week effects, and many others.
TimesFM-3:

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.
Autobox:

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
TimesFM-3:

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
Autobox:

Audience

Forecasters and professionals seeking a solution to load and forecast their data
TimesFM-3:

Audience

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

Support

Phone Support Supported
24/7 Live Support Not Supported
Online Supported
TimesFM-3:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
Autobox:

API

Offers API Not Supported
TimesFM-3:

API

Offers API Not Supported
Autobox:

Screenshots and Videos

TimesFM-3:

Screenshots and Videos

Autobox:

Pricing

No information available.
Free Version Not Supported
Free Trial Supported
TimesFM-3:

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported
Autobox:

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
TimesFM-3:

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
Autobox:

Training

Documentation Supported
Webinars Not Supported
Live Online Supported
In Person Not Supported
TimesFM-3:

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported
Autobox:

Company Information

Automatic Forecasting Systems
United States
autobox.com/cms/index.php/products/autobox
TimesFM-3:

Company Information

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

Alternatives

TimesFM-3:

Alternatives

Timestral

Timestral

Mistral AI
Autobox:
TimesFM-3:
Autobox:
TimesFM-3:
CodeQwen

CodeQwen

Alibaba
Autobox:
TimesFM-3

TimesFM-3

Google
TimesFM-3:
Kimi K2

Kimi K2

Moonshot AI
Autobox:
TimesFM-3:
Qwen-7B

Qwen-7B

Alibaba
Autobox:

Categories

TimesFM-3:

Categories

AI Models Supported
Foundation Models Supported
Autobox:

Integrations

No info available.
TimesFM-3:

Integrations

No info available.
Autobox:
Claim Autobox and update features and information
Claim Autobox and update features and information
TimesFM-3:
Claim TimesFM-3 and update features and information
Claim TimesFM-3 and update features and information