Package: finnts 0.7.0.9018

Mike Tokic

finnts: Microsoft Finance Time Series Forecasting Framework

Automated time series forecasting developed by Microsoft Finance. The Microsoft Finance Time Series Forecasting Framework, aka Finn, can be used to forecast any component of the income statement, balance sheet, or any other area of interest by finance. Any numerical quantity over time, Finn can be used to forecast it. While it can be applied outside of the finance domain, Finn was built to meet the needs of financial analysts to better forecast their businesses within a company, and has a lot of built in features that are specific to the needs of financial forecasters. Happy forecasting!

Authors:Mike Tokic [aut, cre], Aadharsh Kannan [aut]

finnts_0.7.0.9018.tar.gz
finnts_0.7.0.9018.zip(r-4.7-any)finnts_0.7.0.9018.zip(r-4.6-any)finnts_0.7.0.9018.zip(r-4.5-any)
finnts_0.7.0.9018.tgz(r-4.6-any)finnts_0.7.0.9018.tgz(r-4.5-any)
finnts_0.7.0.9018.tar.gz(r-4.7-any)finnts_0.7.0.9018.tar.gz(r-4.6-any)
finnts_0.7.0.9018.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
finnts/json (API)

# Install 'finnts' in R:
install.packages('finnts', repos = c('https://microsoft.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/microsoft/finnts/issues

Pkgdown/docs site:https://microsoft.github.io

On CRAN:

Conda:

agentaibusinessfeature-selectionfinancefinntsforecastingllmmachine-learningmicrosofttime-series

10.38 score 280 stars 43 scripts 620 downloads 69 exports 211 dependencies

Last updated from:3e036efd2f. Checks:5 NOTE, 2 OK, 2 ERROR. Indexed: yes.

TargetResultTimeFilesSyslog
linux-develNOTE1629
source / vignettesOK620
linux-releaseNOTE1763
macos-releaseERROR972
macos-oldrelERROR1745
windows-develNOTE2326
windows-releaseNOTE1757
windows-oldrelNOTE2162
wasm-releaseOK189

Exports:arima_fast_modelarima_fast_model_fit_implarima_fast_model_predict_implask_agentchat_copilotchronos_bolt_base_modelchronos_bolt_base_model_fit_implchronos_bolt_base_model_predict_implchronos_bolt_tiny_modelchronos_bolt_tiny_model_fit_implchronos_bolt_tiny_model_predict_implchronos2_modelchronos2_model_fit_implchronos2_model_predict_implcreate_custom_modelcubist_multistepcubist_multistep_fit_implcubist_multistep_predict_implcustom_model_controlcustom_model_examples_templatecustom_model_feedbackcustom_model_fit_implcustom_model_predict_impldetect_hierarchyensemble_modelsfinal_modelsfinetune_depthfinetune_stepsforecast_time_seriesget_agent_forecastget_best_agent_runget_eda_dataget_forecast_dataget_prepped_dataget_prepped_modelsget_run_infoget_summarized_modelsget_trained_modelsglmnet_multistepglmnet_multistep_fit_implglmnet_multistep_predict_impliterate_forecastlist_modelsmars_multistepmars_multistep_fit_implmars_multistep_predict_implprep_dataprep_modelsset_agent_infoset_project_infoset_run_infosvm_poly_multistepsvm_poly_multistep_fit_implsvm_poly_multistep_predict_implsvm_rbf_multistepsvm_rbf_multistep_fit_implsvm_rbf_multistep_predict_impltimegpt_modeltimegpt_model_fit_impltimegpt_model_predict_impltimesfm_modeltimesfm_model_fit_impltimesfm_model_predict_impltrain_modelsupdate_forecastvalidate_prepared_inputxgboost_multistepxgboost_multistep_fit_implxgboost_multistep_predict_impl

Dependencies:abindanytimeaskpassbackportsbase64encBHbigDbitbit64bitopsbroombslibcachemcallrcheckmateclassclicliprclockcodetoolscolorspacecommonmarkconflictedcpp11crayoncrosstalkCubistcurldata.tabledescdiagramdialsDiceDesigndigestdistributionaldoParalleldplyrdygraphsearthevaluateextraDistrfabletoolsfarverfastmapfeastsfontawesomeforcatsforeachforecastFormulafracdifffsfurrrfuturefuture.applyGauProgenericsggdistggplot2ggtimeglmnetglobalsgluegowergridExtragtgtablegtoolshardhathighrhmshtmltoolshtmlwidgetshtshttrinferinlineipredisobanditeratorsjanitorjquerylibjsonlitejuicyjuicekernlabKernSmoothknitrlabelinglaterlatticelavalazyevallbfgslifecyclelistenvlitedownlmtestloolubridatemagrittrmarkdownMASSMatrixmatrixStatsmemoisemimemixoptmixtimemodeldatamodelenvmodeltimenlmennetnumDerivopensslotelpadrparallellyparsnippatchworkpillarpkgbuildpkgconfigplotlyplotmoplotrixplyrposteriorprettyunitsprocessxprodlimprogressprogressrpromisesprophetpspurrrquadprogquantmodQuickJSRR6rappdirsRColorBrewerRcppRcppArmadilloRcppEigenRcppParallelRcppRollreactablereactRreadrrecipesreshape2rlangrmarkdownrpartrsamplerstanrstantoolsrstudioapirulesS7sassscalessfdshapeslidersnakecaseSparseMsparsevctrssplitfngrSQUAREMStanHeadersstringistringrsurvivalsystailortensorAtibbletidymodelstidyrtidyselecttimechangetimeDatetimetktinytextseriestsfeaturestsibbleTTRtunetzdburcautf8V8vctrsvecvecviridisLitevroomwarpwithrworkflowsworkflowsetsxfunxgboostxml2xtsyamlyardstickzoo

Best Model Selection
Process at a glance | Experimental custom models | Historical-only and future-required drivers | Deterministic Authoring Mechanics | Automatic Authorization | Example Dates and Retries | Source Repair Diagnostics | Manual Review | Reviewed Hierarchy Rules | Custom models in Agent iterations and updates | Future-forecast checks | Supported historical growth | Accuracy allowance | Least-issues fallback | Standard forecasts and saved averages | Reconciliation | Iterative Agent forecasts | Updated Agent forecasts | Updating an earlier update | Changing hierarchy membership | Evidence and limitations | Historical actuals | Backtest weighted MAPE
Rendered frombest-model-selection.Rmdusingknitr::rmarkdown

Last update: 2026-10-26
Started: 2021-08-24

Models Used in finnts
Univariate vs Multivariate Models | Adaptive Daily ARIMA | Global vs Local Models | Ensemble Models | Multistep Horizon Models | Leveraging the Tidymodels Framework
Rendered frommodels-used-in-finnts.Rmdusingknitr::rmarkdown

Last update: 2026-10-26
Started: 2021-08-24

AI Agent Capabilities
Why an AI agent in finnts? | What the agent produces | Approved Custom Models | Updating Approved Choices | Prerequisites | End-to-end: first run with the AI agent | 1) Create a project | 2) Bring data | 3) Define the LLM | Alternative: GitHub Copilot CLI | 4) Create the agent run | 5) Let the agent iterate to a best run | 6) Retrieve results | Ask questions about your forecast results | How it works | Example questions | What data sources are available | Tips for effective questions | Updating with new data (production loop) | Hierarchies (optional) | External regressors (xregs) | Parallelism knobs | Reading artifacts directly (optional)
Rendered fromai-agent.Rmdusingknitr::rmarkdown

Last update: 2026-10-20
Started: 2025-09-08

Hierarchical Forecasting
Selecting a Hierarchy | Standard Hierarchy | Grouped Hierarchy | Reviewed Custom Rules | External Regressors | Spark Parallel Processing | Corner Cases in Forecast Reconciliation
Rendered fromhierarchical-forecasting.Rmdusingknitr::rmarkdown

Last update: 2026-10-20
Started: 2021-08-24

Parallel Processing
Local Machine | Parallel AI Agent Workflows | Within Azure using Spark
Rendered fromparallel-processing.Rmdusingknitr::rmarkdown

Last update: 2026-10-08
Started: 2021-08-24

Forecasting with GenAI
Chronos2 | Authentication and Setup | Using Chronos2 within finnts | Data Size Requirements and Automatic Padding | Global Model Support | Chronos Bolt Base | Using Chronos Bolt Base within finnts | Chronos Bolt Tiny | Using Chronos Bolt Tiny within finnts | TimesFM | Using TimesFM within finnts | TimeGPT | Azure-hosted TimeGPT | Option A: Environment variables | Option B: Using nixtlar helper | Nixtla API | Option A: Environment variable | Quick start with nixtlar (standalone) | Using TimeGPT within finnts | Long-Horizon Forecasting | Hyperparameter Tuning
Rendered fromforecasting-genai.Rmdusingknitr::rmarkdown

Last update: 2026-08-27
Started: 2025-11-03

Quick Start Guide
1. Bring Data | 2. Set Up Agent | 3. Iterate Forecast | 4. Analyze Forecast Output | 5. Update Forecast
Rendered fromfinnts.Rmdusingknitr::rmarkdown

Last update: 2026-08-25
Started: 2021-09-13

Feature Selection
Optional Dependency | Feature Selection Techniques | Target Correlation | Leave One Feature Out (lofo) | Boruta | Model Variable Importance | Voting Process
Rendered fromfeature-selection.Rmdusingknitr::rmarkdown

Last update: 2026-08-25
Started: 2023-08-23

Feature Engineering
Missing Data and Outliers | Understanding "_original" Columns | Box-Cox | Differencing | Date Features | Lags, Rolling Windows, and Polynomial Transformations | Custom Approaches | Model Specific Preprocessing
Rendered fromfeature-engineering.Rmdusingknitr::rmarkdown

Last update: 2026-08-25
Started: 2021-08-24

Back Testing and Hyperparameter Tuning
Rendered fromback-testing-and-hyperparameter-tuning.Rmdusingknitr::rmarkdown

Last update: 2025-09-08
Started: 2021-08-24

Using Individual finnts Forecast Components
Get Data and Set Run Info | Prep the Data | Train Individual Models | Train Ensemble Models | Final Models | Get Forecast Results
Rendered fromforecast-components.Rmdusingknitr::rmarkdown

Last update: 2025-09-08
Started: 2023-05-08

External Regressors
Historical Values Only | Historical and Future Values
Rendered fromexternal-regressors.Rmdusingknitr::rmarkdown

Last update: 2024-07-29
Started: 2021-08-24

Tips for Production
Manage Dependencies | Azure ML Pipelines
Rendered fromtips-for-production.Rmdusingknitr::rmarkdown

Last update: 2023-07-17
Started: 2023-05-08