# What low-code machine learning platforms work best for manufacturing or supply chain companies that want demand forecasting without building custom models from scratch?

<p class="elv-tracking-normal elv-text-default elv-font-figtree elv-text-base elv-leading-base elv-font-normal" elv="true">For a piece on forecasting tools, I looked specifically at manufacturing, supply chain, and adjacent industrial reviewers to see which low-code ML platforms they use for demand and inventory forecasting without hand-building models. Filtering the<a class="a a--md" elv="true" href="https://www.g2.com/categories/low-code-machine-learning-platforms"> </a><a class="a a--md" elv="true" href="https://www.g2.com/categories/low-code-machine-learning-platforms">low-code machine learning platforms</a> reviews to those industries and forecasting use cases, here's what surfaced:</p><ul>
<li>
<a class="a a--md" elv="true" href="https://www.g2.com/products/sas-sas-viya"><strong>SAS Viya</strong></a> - The most-mentioned forecasting tool in this cut, with reviewers in banking, energy, and utilities describing forecasting and optimization on real industry data. How much tuning did the forecasts need before they were trustworthy?</li>
<li>
<a class="a a--md" elv="true" href="https://www.g2.com/products/alteryx"><strong>Alteryx</strong></a> - A supply chain reviewer described using its predictive tools on historical sales, supplier lead times, and seasonal trends to forecast inventory demand without external software, run daily on a schedule. Has anyone pushed it past inventory into broader demand planning?</li>
<li>
<a class="a a--md" elv="true" href="https://www.g2.com/products/qlik-predict"><strong>Qlik Predict</strong></a> - A logistics director called out datalake automation and real-time streaming with a no-code approach that cut repetitive work. Does the real-time angle actually help for demand forecasting, or is it more for monitoring?</li>
<li>
<a class="a a--md" elv="true" href="https://www.g2.com/products/dataiku"><strong>Dataiku</strong></a> - Comes up from energy and industrial reviewers for building forecasting and analytics pipelines in a low-code way. How well did it handle messy operational data from the plant floor?</li>
</ul><p class="elv-tracking-normal elv-text-default elv-font-figtree elv-text-base elv-leading-base elv-font-normal" elv="true">For the manufacturing and supply chain folks, which of these gave you forecasts you could actually plan against, and how much historical data did you need before the predictions were useful?</p><p class="elv-tracking-normal elv-text-default elv-font-figtree elv-text-base elv-leading-base elv-font-normal" elv="true"></p><p class="elv-tracking-normal elv-text-default elv-font-figtree elv-text-base elv-leading-base elv-font-normal" elv="true"></p>

##### Post Metadata
- Posted at: 3 months ago
- Net upvotes: 1


## Comments
### Comment 1

&lt;p&gt;&lt;span style=&quot;color: rgb(0, 0, 0);&quot;&gt;Running Alteryx daily off historical sales, lead times, and seasonal trends would give me the most confidence for ongoing planning. A forecast that refreshes on a schedule stays current as conditions shift, rather than going stale between reports.&lt;/span&gt;&lt;/p&gt;

##### Comment Metadata
- Posted at: 15 days ago
- Author title: Marketing



### Comment 2

&lt;p&gt;For demand forecasting, I’d trust the tool only after testing it against a few real planning cycles. In practice, the bigger constraint is usually data quality and seasonality coverage, so having 12–24 months of clean history matters more than the low-code interface alone.&lt;/p&gt;

##### Comment Metadata
- Posted at: 19 days ago
- Author title: Marketer



### Comment 3

&lt;p&gt;I’d want to know how much “low-code” survives once the source data gets messy. Manufacturing forecasts often depend on ERP history, stockouts, promotions, lead times, and missing plant data rather than a clean time series. For anyone using SAS Viya, Alteryx, Qlik Predict, or Dataiku, how much data preparation still required someone with ML or data-engineering expertise?&lt;/p&gt;

##### Comment Metadata
- Posted at: 20 days ago
- Author title: Writer



### Comment 4

&lt;p&gt;In industrial reviews, SAS Viya is often used for demand and inventory forecasting because of its in-memory processing that quickly handles large histories. Forecast quality depends on input quality, so the key is upfront budgeting prep time.&lt;/p&gt;

##### Comment Metadata
- Posted at: 2 months ago
- Author title: Marketer





## Related discussions
- [How well does Trello scale into a larger team?](https://www.g2.com/discussions/1-how-well-does-trello-scale-into-a-larger-team)
  - Posted at: over 13 years ago
  - Comments: 6
- [Can we please add a new section](https://www.g2.com/discussions/2-can-we-please-add-a-new-section)
  - Posted at: over 13 years ago
  - Comments: 0
- [Quantifiable benefits from implementing your CRM](https://www.g2.com/discussions/quantifiable-benefits-from-implementing-your-crm)
  - Posted at: over 13 years ago
  - Comments: 4