← Back to home
Comparison · Analytics

bbk vs fastml

A side-by-side editorial comparison of bbk and fastml — release velocity, themes, recent moves, and the top alternatives to consider.

bbk vs fastml: at a glance

Featurebbkfastml
SectorAnalyticsAnalytics
Velocity score0.00.0
Sparks · 30d00
Top themescentral-bank-data, macro-statistics, r-package, api-wrapperautoml, tidymodels, survival analysis, cross-validation
Last editorial update4h ago58m ago
WebsiteVisit →Visit →

What is bbk?

One R interface is absorbing the world's central bank data portals, one API at a time.

bbk began as a Bundesbank client and has become a single R interface to central bank statistics generally: the ECB, BIS, and the national banks of Switzerland, Canada, the UK, France, Spain, Austria, Sweden, Norway, Portugal, Japan, Poland, the Czech Republic, and now Brazil and Mexico. Each provider gets a consistent set of verbs — a data function, a dimension function for the dataflow structure, and provider-specific extras like PRIBOR or CZEONIA fixings. Response caching, data.table returns, and an updated_after argument for incremental retrieval are shared plumbing rather than per-provider features.

Read the full bbk trajectory →

What is fastml?

fastml added survival modelling and leakage-proof resampling, moving past classification and regression.

A tidymodels-based AutoML wrapper that trains, tunes and compares many engines from one call. The 0.6.x line added engine-specific tuning parameters, class-imbalance handling, early stopping and DALEX-based explainability. The 0.7.5 release is far larger: a full survival analysis task with its own engines, MICE imputation and integrated Brier scoring, plus unbiased nested cross-validation, grouped, blocked and rolling resampling helpers, fold-wise imputation, recipe leakage checks, and a sandbox for user-supplied preprocessing.

Read the full fastml trajectory →

bbk vs fastml: editorial side-by-side

B
bbk
ANALYTICS
0.0

One R interface is absorbing the world's central bank data portals, one API at a time.

◆ Current state

bbk began as a Bundesbank client and has become a single R interface to central bank statistics generally: the ECB, BIS, and the national banks of Switzerland, Canada, the UK, France, Spain, Austria, Sweden, Norway, Portugal, Japan, Poland, the Czech Republic, and now Brazil and Mexico. Each provider gets a consistent set of verbs — a data function, a dimension function for the dataflow structure, and provider-specific extras like PRIBOR or CZEONIA fixings. Response caching, data.table returns, and an updated_after argument for incremental retrieval are shared plumbing rather than per-provider features.

◆ Where it's heading

The expansion is steady and the integration work is what makes it more than a list of wrappers: arguments introduced for one provider get pushed to the others, dimension introspection is being generalised across dataflows, and the bug fixes in recent releases are almost all about the same class of problem — series with missing observations, unsupported frequency codes, or date/value misalignment breaking a parser written for a tidier feed. The maintainer ships the same infrastructure across their packages in lockstep; bbk 0.9.0 and the sibling treasury package's 0.5.0 landed identical opt-in caching within minutes of each other. Geography is the visible frontier, but consistency across an increasingly ragged set of upstream APIs is the actual work.

◆ Prediction

Expect more national central banks to be added on the same template, and the newer providers to be retrofitted with the dimension and updated_after functions the older ones already have.

F
fastml
ANALYTICS
0.0

fastml added survival modelling and leakage-proof resampling, moving past classification and regression.

◆ Current state

A tidymodels-based AutoML wrapper that trains, tunes and compares many engines from one call. The 0.6.x line added engine-specific tuning parameters, class-imbalance handling, early stopping and DALEX-based explainability. The 0.7.5 release is far larger: a full survival analysis task with its own engines, MICE imputation and integrated Brier scoring, plus unbiased nested cross-validation, grouped, blocked and rolling resampling helpers, fold-wise imputation, recipe leakage checks, and a sandbox for user-supplied preprocessing.

◆ Where it's heading

The package is moving from convenience wrapper to something that has to be defensible statistically. Nested cross-validation, fold-wise rather than up-front imputation, and explicit leakage checks are all corrections to the shortcuts that make AutoML easy and its scores optimistic. Survival adds a third task type alongside classification and regression, and it arrived with its own metrics rather than being bolted onto the existing ones. Note the entry body is cut off at 8,000 characters, so the release is larger than what is shown.

◆ Prediction

Expect the remaining survival engines to fill in and the sandboxing of custom preprocessing to tighten, since both were still being iterated on within this same release's commit list.

Alternatives to bbk and fastml

Other Analytics products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either bbk or fastml.

See all bbk alternatives → · See all fastml alternatives →

Recent activity from bbk and fastml

Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.

  1. 1mo agobbkBrazil and Mexico join, bringing survey expectations data
  2. 2mo agobbkCzech National Bank support lands with a broad parser repair
  3. 3mo agobbkIncremental retrieval generalised beyond the ECB endpoint
  4. 4mo agobbkOpt-in response caching plus dimension introspection everywhere
  5. 8mo agofastmlVersion 0.7.5
  6. 10mo agobbkBank of Canada data and exchange rates added
  7. 11mo agobbkFour European central banks added; validation moves to checkmate
  8. 1y agofastmlEngine-specific tuning, imbalance handling and explainability
  9. 1y agofastmlSingle-workflow evaluation fix
  10. 1y agofastmlVersion 0.5.0

Frequently asked questions

What is the difference between bbk and fastml?

They serve adjacent needs but don't currently overlap on shipped themes. bbk and fastml are shipping at a similar cadence (velocity 0.0 vs 0.0, both within Sparkpulse's "active" band). See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.

Is bbk better than fastml?

Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. bbk and fastml are shipping at a similar cadence (velocity 0.0 vs 0.0, both within Sparkpulse's "active" band). For your specific use case, the alternatives sections above list other Analytics products to evaluate alongside.

What are the best alternatives to bbk?

Top bbk alternatives in Analytics are ranked by recent ship velocity. Browse the "bbk alternatives" section above for the current picks, or visit /alternatives/bbk for the full list with editorial commentary on each.

What are the best alternatives to fastml?

Top fastml alternatives in Analytics are ranked by recent ship velocity. Browse the "fastml alternatives" section above for the current picks, or visit /alternatives/fastml for the full list with editorial commentary on each.