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.

Share on FacebookShare on Google+Share on LinkedInTweet about this on TwitterEmail this to someone

How IoT logistics will revolutionize supply chain management

As with many other areas of the economy, the digital revolution is having a profound effect on delivery logistics.

The combination of mobile computing, analytics, and cloud services, all of which are fueled by the Internet of Things (IoT), is changing how delivery and fulfillment companies are conducting their operations.

One of the most popular methods for fulfilling deliveries today is through third-party logistics, which involves any company that provides outsourced services to move products and resources from one area to another. Third-party logistics, or 3PL, can be one service, such as transportation or a warehouse, or an entire system that maintains the whole supply chain.

But the IoT is going to change how this process operates. Below, we’ve outlined the impact of IoT on supply chain, and how IoT management will transform inventory, logistics, and more.

Internet of Things Supply Chain Management

One of the biggest trends poised to upend supply chain management is asset tracking, which gives companies a way to totally overhaul their supply chain and logistics operations by giving them the tools to make better decisions and save time and money. Delivery company DHL and tech giant Cisco estimated in 2015 that IoT technologies such as asset tracking solutions could have an impact of more than $1.9 trillion in the supply chain and logistics sector.

And this transformation is already underway. A recent survey by GT Nexus and Capgemini found that 70% of retail and manufacturing companies have already started a digital transformation project in their supply chain and logistics operations.

Asset tracking is not new by any means. Freight and shipping companies have used barcode scanners to track and manage their inventory. But new developments are making these scanners obsolete, as they can only collect data on broad types of items, rather than the location or condition of specific items. Newer asset tracking solutions (which we’ll get into shortly in the next section) offer much more vital and usable data, especially when paired with other IoT technologies.

Read more at How IoT logistics will revolutionize supply chain management

We would like to know what you think about this topic, share your opinions with us in the comment box. If you need assistance, you can contact us via email. You can subscribe us to be the first one to get the latest article.

Share on FacebookShare on Google+Share on LinkedInTweet about this on TwitterEmail this to someone

5 Critical Supply Risk Mitigation Principles for Your Sourcing Process

Supply chain risk management (SCRM) is becoming a top priority in procurement, as organizations lose millions because of cost volatility, supply disruption, non-compliance fines and incidents that cause damage to the organizational brand and reputation.
Bribes to shady government officials, salmonella in the spinach and forced labor in the supply chain can all result in brand-damaging headlines that can cost an organization tens of millions in sales and hundred of millions in brand damage. And while reputation may only be important for name brands, cost volatility and supply disruption affect all manufacturers.

In fact, in the latest 2015 study by the Business Continuity Institute, supply chain disruption doubled in priority relative to other enterprise disruptions (48% of firms are concerned or extremely concerned). Roughly three-quarters of respondents said they had at least one disruption, and the same amount lack full visibility of their supply chains.

In the same study, 14% had losses from supply chain disruptions (e.g., natural hazards, labor strikes, fires, etc.) that cost over €1 million, and these disruptions can easily go up to nine figures. For example, Toyota estimates the costs for the recent Kumamoto earthquakes to be nearly $300 million. Imagine being out of stock on a product line that does $12 million in annual sales for two months. That’s $2 million in immediate lost sales and longer-term brand damage.

Risk management, and what is necessary for ongoing risk management, never gets operationalized, and as new suppliers get added, supply shifts and supply chains change, new risk enters the picture — risks that go undetected unless risk management is embedded in all key procurement activities, including sourcing. It is important to remember that:

1. When You are Sourcing, You are Really Changing Your Supply Chain Network

2. Supplier Risk is Only One Aspect of Supply Chain Risk

3. Your Sourcing Criteria Must Be ‘Protected’ and Risk Must Be Factored In

4. You Need to Cost the Risk” and Also Get It in the Contract

5. You Must Design a Monitoring System That is Part of Onboarding

Read more at 5 Critical Supply Risk Mitigation Principles for Your Sourcing Process

Share your opinions with us in the comment box and subscribe to get updates in your inbox.

Share on FacebookShare on Google+Share on LinkedInTweet about this on TwitterEmail this to someone