How can Lean Six Sigma help Machine Learning?

Note that this article was submitted and accepted by KDnuggest, the most popular blog site about machine learning and knowledge discovery.

I have been using Lean Six Sigma (LSS) to improve business processes for the past 10+ year and am very satisfied with its benefits. Recently, I’ve been working with a consulting firm and a software vendor to implement a machine learning (ML) model to predict remaining useful life (RUL) of service parts. The result which I feel most frustrated is the low accuracy of the resulting model. As shown below, if people measure the deviation as the absolute difference between the actual part life and the predicted one, the resulting model has 127, 60, and 36 days of average deviation for the selected 3 parts. I could not understand why the deviations are so large with machine learning.

After working with the consultants and data scientists, it appears that they can improve the deviation only by 10%. This puzzles me a lot. I thought machine learning is a great new tool to make forecast simple and quick, but I did not expect it could have such large deviation. To me, such deviation, even after the 10% improvement, still renders the forecast useless to the business owners.

Read more at How can Lean Six Sigma help Machine Learning?

Leave your comments below and subscribe us to get updates in your inbox.

Great Suppliers Make Great Supply Chains

As an analyst who covers supply chain management (SCM) and procurement practice across industry, I tend to keep my keyboard focused on the disruptive themes that continue to re-define it. That said, if you’re expecting me go on about the unprecedented growth of the SCM solution markets, the accelerated pace of innovation, tech adoption, social change, etc., don’t hold your breath. I can’t, as the data argue otherwise. Too many of us conflate diversification with acceleration –and there’s a difference.

The most notable, defining advances of the last decade (Amazon, Twitter, Google, etc.) share something in common: they do not require consumer investment. If you take those monsters out of the equation and focus on corporate solution environments, the progress, while steady, has not been remarkable. Let’s just say there remains plenty of room for improvement, especially in supply chain and procurement practice areas.

I fell onto this tangent unexpectedly. It happened while interviewing Mr. Dan Georgescu, Ford Motor Company, adjunct Professor of Operations and Supply Chain Management, a highly regarded expert in the field of automotive industry supplier development. “For supply chains to be successful, performance measurement must become a continuous improvement process integrated throughout,” he said. “For a number of reasons, including the fact that our industry is increasingly less vertically integrated, supplier development is absolutely core to OEM performance.”

Read more at Great Suppliers Make Great Supply Chains

If you have any comments about this topic, share it with us below. Subscribe to get updates in your inbox.

SenseAware is FedEx’s Internet of Things Response to Supply Chain Optimization

Supply chain visibility is critical to a company’s operational performance improvement, according to 63% of 149 responding companies in a survey conducted by Aberdeen Group.

“Visibility is a prerequisite to supply chain agility and responsiveness,” the report states.

And it requires tracking the location of a shipment not only at the transportation level, but also at a unit and item level.

Location tracking is good protection against shipment theft or loss, but companies need a deeper level of visibility for their products, according to FedEx.

The company’s solution? The IoT-inspired SenseAware, a sensor-based logistics solution.

SBL uses sensors to detect the shipment’s environmental conditions while warehoused or in transit and sends the data – via wireless communication devices – to a management software system where the data is collected, displayed, analyzed and stored.

It is “the basis of a powerful new central nervous system for the global supply chain,” according to FedEx.

The device is meant to provide intelligence that can help enterprises coordinate and manage product, information and financial flows.

Read more at SenseAware is FedEx’s Internet of Things Response to Supply Chain Optimization

If you have any opinions, write them below or contact us for discussion. Subscribe us to get updates in your inbox.

How to Use Big Data to Enhance Employee Performance

Big Data has been one of the most significant and influential aspects of the Information Age as it relates to the enterprise world. Essentially, Big Data is the massive collection, indexing, mining, and implementation of information that emanates from just about any activity that can be monitored and managed electronically. Some of the uses of Big Data include: marketing intelligence, sales automation, strategizing, productivity improvement, and efficient management.

Enhancement of the workforce is one of the exciting and meaningful benefits of Big Data for the business sphere. Recently, human resource managers and analysts have been researching the implementation of Big Data as it relates to employees, and the following trends have emerged:

Employee Intelligence

For many decades, companies and organizations have tried various methods to gain knowledge about what their employees are really like. The productivity that workers can contribute to their employers is based on personal needs as they are balanced against the performance of their duties. With Big Data solutions, both personal needs and performance can be diluted into metrics for efficient analysis.

Modern workplace analytics originates from tracking employee records as well as metrics on their performance, interactions and collaboration. The idea is to focus on the right metrics to create a climate of positive engagement.

Read more at How to Use Big Data to Enhance Employee Performance

Share your opinions about this topic and subscribe to get updates in your inbox.