IT Pro is supported by its audience. When you purchase through links on our site, we may earn an affiliate commission. Learn more

Google brings no-code machine learning to Sheets with SimpleML

Businesses looking to automate their Google workspaces could benefit from the tool which requires no programming experience and is now in beta

Google has released Simple ML, a tool to help apply machine learning to data prediction and sorting tasks within Google Sheets. 

Available as an add-on, the tool is intended to be stress-free to install and use, while powerful in its potential applications. Using a sheet with at least two columns, users can quickly train and refine a machine learning model to their own needs, opening up possibilities for automation across a company’s existing Google Workspace.

Related Resource

Flexible IT models drive efficiency and innovation

A modern approach to infrastructure management

Whitepaper cover with image of woman in glasses sat at a computerFree Download

The tool is intended to enable enhanced activity in Sheets for both beginners and advanced users. It can be used for tasks like predicting how long maintenance could take based on past data, or spotting potential fraud when analysing unusual data in a client's finances. 

By default, the tool is shipped with two functions: ‘predict missing values’ and ‘spot abnormal values’. For more complex use, it can even predict values within large data sets - Google gave the example of researchers using Simple ML to predict a person’s age based on their DNA in a molecular ageing study.

Simple ML was made by the same developers as TensorFlow, and is pre-trained to be as effective at processing data as possible. Despite the complicated nature of ML algorithms, and to combat the intense learning curve traditionally associated with training and deploying a machine learning (ML) model, the tool can be used on a fully no-code basis.

Nevertheless, advanced users that are already familiar with training machine learning models still seek to benefit from Simple ML, which allows for detailed evaluation of models to understand the quality of models that they have trained using the tool.

Models are broken down into a number of metrics, depending on the way the model was originally trained, and demonstrated through data and graphical representations.

Google recommends using Simple ML on sheets which contain columns with at least 20 values, though 100 is the recommended number for a model to really start training with accuracy.

Depending on the complexity of the task, far more may be required, and when a task cannot be completed, a detailed error message indicates what has prevented the model from running as intended.

A key benefit of the service, as cited by Google, is the fact that it runs entirely in a browser, so all sensitive data that could be included on a Sheet remains secure.

In addition, ML models are saved directly to Google Drive in their own folder, enabling them to be shared between a team in a business environment or downloaded for backup should they be crucial to new business processes.

In a blog post on the release, Google outlined the ease of use by listing the three steps necessary: opening the data; selecting the task that suits the use case, such as identifying anomalous data; running the model and seeing the results, which are weighted by probability.

On a technical level, Simple ML utilises decision forests - a group of randomly-generated decision trees governed by a machine learning algorithm to output predictive results.

Google announced the update at the annual Women in ML Symposium, an online event held by the firm to promote an inclusive community within the field. Simple ML is available right now in beta. 

Featured Resources

2023 Strategic roadmap for data security platform convergence

Capitalise on your data and share it securely using consolidated platforms

Free Download

The 3D trends report

Presenting one of the most exciting frontiers in visual culture

Free Download

The Total Economic Impact™ of IBM Cloud Pak® for Watson AIOps with Instana

Cost savings and business benefits

Free Download

Leverage automated APM to accelerate CI/CD and boost application performance

Constant change to meet fast-evolving application functionality

Free Download

Recommended

Google to cut global workforce by 12,000 roles
Careers & training

Google to cut global workforce by 12,000 roles

20 Jan 2023
Google Ads malvertising campaign prompts questions around Search security
malware

Google Ads malvertising campaign prompts questions around Search security

18 Jan 2023
Microsoft pins hopes on ChatGPT to supercharge Bing search engine
artificial intelligence (AI)

Microsoft pins hopes on ChatGPT to supercharge Bing search engine

4 Jan 2023
Gmail vs Outlook: Which one is better for business?
email providers

Gmail vs Outlook: Which one is better for business?

23 Dec 2022

Most Popular

Warning issued over ransomware attacks targeting VMware ESXi servers globally
cyber attacks

Warning issued over ransomware attacks targeting VMware ESXi servers globally

6 Feb 2023
ION Trading reportedly pays LockBit ransom demands
ransomware

ION Trading reportedly pays LockBit ransom demands

6 Feb 2023
BT Group extends Kyndryl deal to migrate legacy mainframe apps to the cloud
Business strategy

BT Group extends Kyndryl deal to migrate legacy mainframe apps to the cloud

31 Jan 2023