Softwr

Energy · head to head

Novity vs Apache Spark MLlib

Novity logo

Novity

Energy

Hybrid physics and machine learning prognostics that estimate remaining useful life for process equipment

From
On request
Rated
-
Full reviewWebsite
Apache Spark MLlib logo

Apache Spark MLlib

Machine Learning

The machine learning library inside Apache Spark, for data that will not fit on one machine

From
Free
Rated
-
Full reviewWebsite

The short version

  • Only Apache Spark MLlib has a free tier, so it costs nothing to try first.
  • Each has a real cost: Novity novity is a small venture-backed company with a strategic investor rather than a profitable business, so continuity risk is real and the Tokyo Gas investment signals a likely eventual acquisition that would reset the roadmap.; Apache Spark MLlib the algorithm set has grown slowly and its gradient boosting does not match XGBoost or LightGBM in accuracy or speed, so teams routinely do feature engineering in Spark and then train elsewhere, which undoes the argument for using it at all.
  • They diverge on capability: Novity covers TruPrognostics engine, Apache Spark MLlib covers DataFrame-based pipelines.
  • Prices and features above were last checked on 1 September 2026.

Where they differ

Only the attributes on which Novity and Apache Spark MLlib actually diverge.

Attributes where Novity and Apache Spark MLlib differ
AttributeNovityApache Spark MLlib
Starting priceOn requestFree
Pricing modelquoteopen-source
Free tierNoYes
PlatformsWeb, CloudLinux, macOS, Windows
CategoryEnergyMachine Learning
FoundedUnknown1999

Identical on both: user rating (Not yet rated).

What each one covers

Drawn from each product's published feature list. An absence here means we hold no record of it - not that the product lacks it.

Only in Novity

  • TruPrognostics engine
  • Cold-start modelling
  • Fault mode diagnosis
  • Remaining useful life
  • Existing sensor reuse
  • Recommended actions
  • Historian connectors
  • Asset class libraries

Only in Apache Spark MLlib

  • DataFrame-based pipelines
  • Distributed algorithms
  • Alternating least squares
  • Feature transformers
  • Model selection
  • Pipeline persistence
  • Language bindings
  • Runs in existing Spark deployments

What people use each for

The jobs each tool is most often brought in to do.

Novity

  • A gas processing plant that needs a defensible time-to-failure number before deferring a turnaroundnot Apache Spark MLlib
  • An LNG terminal with critical compressors and no run-to-failure history to train a conventional modelnot Apache Spark MLlib
  • A wastewater operator whose existing vibration alarms are ignored because they carry no severity or horizonnot Apache Spark MLlib
  • A generator operator supplying data centre load where an unplanned trip carries contractual penaltiesnot Apache Spark MLlib

Apache Spark MLlib

  • Training on a data set too large to hold on one machine, where sampling down would lose the rare events you care aboutnot Novity
  • Feature engineering and model fitting in one job over tables already in the lake, avoiding an extract and a second copy of sensitive datanot Novity
  • Batch scoring of hundreds of millions of rows on a schedule, where throughput matters and per-request latency does notnot Novity
  • Organisations that already run and pay for Spark, where adding a modelling step is cheaper than introducing a second platformnot Novity

Where each one falls short

Documented limitations, not opinions. Every one is a constraint you would hit in normal use.

Novity

  • Novity is a small venture-backed company with a strategic investor rather than a profitable business, so continuity risk is real and the Tokyo Gas investment signals a likely eventual acquisition that would reset the roadmap.
  • Physics-based models must be configured per equipment class, so each new asset type is an engineering engagement rather than a configuration screen, and rollout speed is limited by Novitys own capacity.
  • Prognostics depend on the quality and sampling rate of your historian data; plants recording ten-minute averages will not get useful remaining-useful-life estimates without new instrumentation.
  • Nothing about pricing is published and there is no self-service entry point, so evaluation always starts with a sales-led pilot on a handful of assets.
  • The deployment footprint is concentrated in oil and gas, LNG and water, so reference customers and pre-built asset models outside those industries are limited.

Apache Spark MLlib

  • The algorithm set has grown slowly and its gradient boosting does not match XGBoost or LightGBM in accuracy or speed, so teams routinely do feature engineering in Spark and then train elsewhere, which undoes the argument for using it at all.
  • There is no deep learning in MLlib; neural network work on Spark requires a separate integration, and the DataFrame-centred interface is an awkward fit for it.
  • Fitted models serialise into Spark's own format, so low-latency serving needs either a Spark session in the request path, which is far too slow, or a conversion through ONNX or MLeap, and this is where most Spark ML projects stall.
  • Debugging is JVM cluster debugging: executor out-of-memory, shuffle spill, skewed partitions and serialisation failures, so an engineer without Spark operations experience spends more time tuning the cluster than improving the model.
  • The cluster is the real cost and Spark holds executors for the duration of a job, so a badly partitioned training run pays for idle cores across the whole fleet while one straggler task finishes.

Pricing, plan by plan

Novity

On request
  • TruPrognostics$undefined/year
    • Quoted per asset class and monitored equipment count
    • Model configuration and commissioning quoted as a project
    • Typically an annual subscription tied to a pilot then a rollout

Apache Spark MLlib

Free

No published plan breakdown. See the Apache Spark MLlib review.

Which should you pick?

Choose Novity if

  • You need truprognostics engine.
  • You work on Web, Cloud.
  • You also want cold-start modelling.
Novity review

Choose Apache Spark MLlib if

  • You need dataframe-based pipelines.
  • You want to start without paying.
  • You work on Linux, macOS, Windows.
  • You also want distributed algorithms.
Apache Spark MLlib review

Questions people ask

Is Novity or Apache Spark MLlib better?
Neither clearly leads. Novity starts at On request and Apache Spark MLlib at Free, and user ratings are close enough to be indistinguishable. Choose on capability and platform support.
Which is cheaper, Novity or Apache Spark MLlib?
Apache Spark MLlib has a free tier; the other does not. Paid plans start at On request for Novity and Free for Apache Spark MLlib.
Does Novity or Apache Spark MLlib run on more platforms?
Novity runs on Web, Cloud. Apache Spark MLlib runs on Linux, macOS, Windows.
Can I use Apache Spark MLlib for free?
Yes. Apache Spark MLlib has a free tier, so you can try it without paying. Novity starts at On request.
What is Novity best used for?
Novity is most often used for a gas processing plant that needs a defensible time-to-failure number before deferring a turnaround, an lng terminal with critical compressors and no run-to-failure history to train a conventional model, a wastewater operator whose existing vibration alarms are ignored because they carry no severity or horizon, a generator operator supplying data centre load where an unplanned trip carries contractual penalties. Of those, a gas processing plant that needs a defensible time-to-failure number before deferring a turnaround and an lng terminal with critical compressors and no run-to-failure history to train a conventional model are not what Apache Spark MLlib is typically brought in for.
What can Novity do that Apache Spark MLlib cannot?
Novity covers TruPrognostics engine, Cold-start modelling, Fault mode diagnosis, Remaining useful life. Apache Spark MLlib covers DataFrame-based pipelines, Distributed algorithms, Alternating least squares, Feature transformers.

Answered from the vendors’ own pages

Novity: What does Novity actually output?

A named failure mode and an estimated remaining useful life with a confidence band, not just an anomaly alert.

Apache Spark MLlib: What is the difference between spark.ml and spark.mllib?

spark.ml is the DataFrame-based interface and the one to use. spark.mllib is the older RDD-based package, kept for compatibility, in maintenance and receiving no new features.

Novity: Do we need failure history to train it?

No. The physics component is what lets it produce useful prognostics on equipment with little or no run-to-failure data.

Apache Spark MLlib: Do I need a cluster?

Spark runs in local mode on one machine, which is useful for development, but if you are running on one machine you would generally be better served by scikit-learn or XGBoost, which are faster and more capable at that scale.

Novity: Do we need new sensors?

Often not. It reads from your existing historian, but low sampling rates or missing measurements can require additional instrumentation.

Apache Spark MLlib: Can I use scikit-learn on Spark instead?

Yes, and it is often the better answer. You can distribute independent model fits across the cluster, or use pandas user-defined functions to run per-group models, keeping Spark for the data and a mature library for the modelling.

Novity: Who backs the company?

It was spun out of Xerox PARC and took a strategic investment from Acario Innovation, the venture arm of Tokyo Gas, in 2026.

Apache Spark MLlib: How do I serve an MLlib model in real time?

Not directly. Either convert the pipeline to a portable format such as ONNX or MLeap, or reimplement the scoring path. Starting a Spark session per request adds seconds of overhead and is not a serving strategy.

Apache Spark MLlib: Is it free?

The library is Apache 2.0 and costs nothing. The cluster it runs on is billed by your cloud provider or by Databricks, and that is the actual expense.

Share

Related pages

More on Novity

More on Apache Spark MLlib

Keep looking

Other head to heads