Big data for analytics and prediction in warehouse production.

In order to increase efficiency and/ quality, you need to analyze the current workflow and working methods. For that, you must be able to collect and work with clear and reliable data. This is one of the reasons I propagate for an established WMS. The analytic tools is definitely features to look at when investing in a WMS. The system should also have a good interface to connect to other systems like for example TMS (transport management system) and/or LMS (labor management system).

Something important to keep in mind is that the quality of the data you get out of the system will never be better than the data you get into the system. For example basic data such as volume, weight, hours etc.

Examples of features for analyzing is:  inventory optimization tools that can help you plan your warehouse layout and picking routes based on shortest forklift driving distance or picking frequency; replenishment analysis specific to customers or target regions; workforce management tools that track total and individual time for each department and task in the warehouse and also can give you forecasts regarding man-hours you need at each department. Some WMS have simulation and visualization tools to make it easy to find time thieves and areas in the warehouse where you can improve the flow. The system can help you locate bottlenecks in the flow. It is easy to place too many high-frequency items in the same aisle or rack.

When you reach a certain point where you feel that your employees have a great pace and their performance have reached the limit you need to work scientifically (with facts) and methodical with help of data and analytical tools to take your warehouse performance to the next level. You need to look at where you spend most hours in the warehouse and how you can make that area more efficient, maybe with help of features in your WMS. You want as few human “touches” on the products as possible from the products arrive to the products leave the warehouse. Every touch or every extra meter on the forklift decrease the value of the product. With good analytical tools, you can make these “touches” and extra meters visible and change the flow to the better. In addition, with help of performance tools in WMS you can see the effects of your changes.

Big data will be an increasingly important part of the work to develop warehouse production. I think those WMS vendors who will be successful in the future must broaden their product portfolio with more advanced modules. They must be able to offer for example, integrated LMS, TMS and advanced interfaces to connect with IoT hardware like forklifts, RFID, tablets and smartglasses. They must also be able to gather and consolidate data in a good way, as well as be able to visualize the information to the management teams.

The most successful WMS vendors in the future is the ones who can develop technology to use big data for prediction of near future scenarios in the warehouse. That would really help companies save money for example in labor and transport costs. It is important the WMS have great ability to gather data from other systems like ERP (purchasing), TMS and LMS and also IoT hardware to analyze data and make more precise predictions of for example workload in different tasks in warehouse and how many man hours you need in every task. It is important the systems have access to data as early as possible to analyze and make forecasts

Remember; for a successful warehouse, you need to be able to collect and analyze data and make use of it together with great leadership and communication skills.

Roberth Karlsson

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s