Effective data analytics in Manufacturing

February 27, 2018
By

[This article was first published on Mango Solutions, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

Data analytics is rapidly changing the face of manufacturing as we know it. At Mango, we’re seeing companies using their data effectively to gain an advantage over competitors.

These companies are using data science to properly set up and control manufacturing For example, automatically adjusting parameters for specific parts/production lines to decrease wastage and meet demand. Research has shown that 68% of manufacturers were already investing in data science to achieve a range of improvements. This means that more than 30% of manufacturers still haven’t adopted a data-driven approach and are therefore not yet working leaner, smarter, improving yields and reducing costs for an increased bottom line.

We know that manufacturing is an asset-intensive industry and companies need to move fast, be more innovative and work smart in order to be competitive. To remain ahead of the game, manufacturers need to adopt a different way of thinking when it comes to data. However, any transition from the industrial to the digital age can be both daunting and a minefield.

Too much data

One of the main problems for many companies —especially within the manufacturing sector— is the speed at which they are collecting massive amounts of real-time data, making it hard to work out what data is actually important. This is even harder without the right tools.

A solution – building a data science capability

To understand their data better, many organisations have started to build teams of Data Scientists. The Data Scientist is indeed becoming an increasingly valuable asset within any organization looking to make the most of their data.

The aim of building a data science capability is to harvest and analyse the data being collected to drive business change. However, many companies struggle to get the right skillsets in their team. In response to this need, we developed the Data Science Radar. The Radar is a conceptual framework that explores character traits and it is a visual aid to support our customers to build and shape an existing data science team, identifying gaps in skillsets and monitoring learning needs. The application has been such a success we provide it free to help companies start their data-driven journey. Take a look at the Data Science Radar here: www.dsradar.com

Choosing the right tools for the job

Data science requires tools that go beyond the capabilities of spreadsheet programs like Excel —which is still often the tool used for data analysis in manufacturing. It is a common, but false, belief that the only alternatives to this are expensive off-the-shelf software packages, which can differ greatly in terms of cost, usability data capacity and visualisation capabilities.

While we use a range of cutting edge tools for our projects, we often recommend one being used around the world by thousands of analysts – the open source R language. From computational science to extensive marketing techniques, R is the most popular analytic language in the world today and a fundamental analytic tool within a range of industries. The growth and popularity of R programming has been helping data-driven organisations succeed for years.

Our knowledge, experience and passion for Data Science means we have engaged in some truly amazing analytic projects. We understand the challenges faced by the manufacturing industry and have worked with companies all over the world to lower product development and operating costs, increase production quality, improve customer experience, and improve manufacturing yields – all using the power of R!

Analytics for non-technical stakeholders

Visualization tools communicate the results of analytics in a clear and precise manner. It’s possible you may have overheard Shiny in discussions between your data analysts and noted it in some of the below case studies. But what is Shiny?

Shiny combines the computational power of R with the interactivity of the modern web. It is a powerful and popular web framework for R programmers to elevate the way people —both technical and non-technical decision makers— consume analytics.

R allows data scientists to effectively analyse large amounts of real-time data but Shiny visualises that data effectively and easily to present outputs for non-analysts, allowing non-technical stakeholders to easily review and filter the data. Outputs can then be hosted on a client’s own servers or via RStudio’s hosting service.

Here are just a few examples of our successful projects:

Mango delivered a large SAS to R migration project with a global semiconductor manufacturer. A complex Shiny application was created to replace the expensive SAS application software already in use. This made it possible to exit an expensive SAS license and adopt modern analytic techniques. This has resulted in improved production yields, reduced costs and enthused production teams with a modern production infrastructure.

Mondelēz were using a SAS Roast Coffee Blend Generator. Mango used advanced prescriptive analytics to migrate the client to R, resulting in optimization of their coffee recipe, improved yield qualities and reduced production costs.

Mango helped a global agrochemical company by providing an in-depth code review of their Shiny application, including modification of code to improve performance. A pack of Shiny coding best practices was also developed by Mango for the client to reference in their future developments, thus helping them improve performance and yields.

Campden BRI have a large Consumer and Sensory Science department who perform comprehensive analysis on sensory and consumer data. Due to years of adding additional features to their exisiting database, the internal systems had come to rely on a restrictive ‘jigsaw of legacy code’. Using R, Mango helped rationalise the work flows and processes to provide a more robust solution, which resulted in a neat application that users could use intuitively. The team have streamlined their work and their use of software packages, saving time, money and effort.

Names have been removed where required, more case examples can be found on our website.

Why Mango?

Mango Solutions have been long-term trusted partners with companies in a wide range of industries, including Manufacturing, Pharmaceutical, Retail, Travel, Automotive, Finance, Energy and Government since 2002. Our team of Data Scientists, Data Engineers, Technical Architects and Software Developers deliver independent, forward thinking, critical, predictive and prescriptive analytical solutions.

Mango have assisted hundreds of companies reap the business gains that come from effective data science because our unique mix of both technical and commercial real-world experience ensures best practice approaches.

Are you ready to become data-driven? Please contact us for an obligation-free conversation today with Christina Halliday: [email protected] or +44(0)1249705450

*RStudio is a partner of Mango Solutions and the creators of Shiny and Shiny commercial products.

To leave a comment for the author, please follow the link and comment on their blog: Mango Solutions.

R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.



If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook...

Comments are closed.

Search R-bloggers

Sponsors

Never miss an update!
Subscribe to R-bloggers to receive
e-mails with the latest R posts.
(You will not see this message again.)

Click here to close (This popup will not appear again)