Isabelle Badoc, Product Marketing Manager, Generix Group, Author at Global Trade Magazine

In its constant pursuit of efficiency, the Supply Chain sector can now count on new technologies resulting from Big Data to improve the performance of its activities. The abundance and diversity of data generated every day by its various actors have allowed the emergence of a multitude of very attractive applications. But when it comes to artificial intelligence (AI), the key lies in the collaboration between Human and Machine. How is this articulation between human intelligence and algorithms established? What is the place of the human being in the development of a connected supply chain? Answers in this article.

A new era for Supply Chain Management

Driven by academic research and large companies like Walmart and Procter & Gamble, the logistics industry underwent its first major transformation in the 1990s. While some players are still working on implementing best practices, Big Data is now revolutionizing the supply chain again.

Under the name “Supply Chain 4.0″ or “Connected Supply Chain”, these promising advances are the result of teams of Data Scientists exploiting artificial intelligence, blockchain, or even robotics. These technologies aim to make the supply chain more agile, predictable and profitable for organizations. How can they do this? By shortening lead times, fully automating demand forecasting, and improving on-time production and delivery.

The Contributions of Data Science to the Supply Chain sector

Improve anticipation of demand

Capable of exploiting very large and diversified sources of information, Data Science and Machine Learning are particularly interesting for identifying trends in a very large quantity of data.

In the Supply Chain sector, Data Science is used in particular to:

-identify weak signals to be actively monitored in order to elaborate prospective choices;

-integrate data from different sources (web…);

-group products according to different consumption behaviors;

-highlighting action strategies adapted to each situation.

Optimize the management of logistics flows

In terms of warehouse management, data analysis can be correlated with certain external factors (raw material supply problems, goods traffic, weather conditions, etc.) to help companies reduce the risk of disruption.

To facilitate the choice of carriers and optimize the organization of delivery rounds, many factors can be taken into account: costs, type of products to be handled, specific transport standards and conditions, packaging, road traffic…

By optimally distributing tasks according to the warehouse’s own data, AI algorithms also contribute to a better allocation of resources and thus allow for greater efficiency.

Improve customer relations

With Data Science, the relationship established with consumers is also becoming more and more personalized. Unsupervised Machine Learning algorithms allow us to segment our customers very finely in order to target promotional offers and services to each profile.

Combined with the analysis of customer feedback, this segmentation data provides valuable information on the steps to be taken to improve customer satisfaction, which remains a core concern for any supply chain.

Human/machine collaboration: a key issue for Data Science

From data to action

In any artificial intelligence process, the autonomy given to the machine takes place gradually. This Gartner graphic shows how the work entrusted to the systems (in blue) is gradually replacing human intervention (shown in green).

The collaboration between human and machine then takes place in 4 main stages:

1. the analysis of the data by the machine (Analytics);

2. the human intervention necessary to interpret the data (Human input);

3. the resulting decision (Decision);

4. the transformation into concrete action (Action).

As time goes by, the amount of autonomy left to the machine is increased, until we can obtain total confidence in the system. But to make the machine capable of deciding as well as the human, a phase of collaboration is essential during the various stages of development of the algorithm. It is more or less long and advanced according to the degree of autonomy wished.

The different types of algorithms

Depending on the nature and intensity of the collaboration between human and machine, there are three main types of machine learning algorithms: supervised, unsupervised and reinforcement learning.

Supervised learning

In supervised mode, the algorithms work from data chosen by humans for their characteristics and their known impact on the result. For example: the outdoor temperature curve influences beverage sales, or the number of orders to be shipped impacts the picking load in the warehouse. Sales forecasting models use this type of algorithm in particular.

The intelligence is in this case mainly provided by the human. The machine is then mainly used for its calculation capacities on the basis of several series of data.

Unsupervised learning

The objective here is to meet 2 specific objectives:

-to create clusters, meaning groups of individuals with similar behaviors, in order to define management rules that are refined and therefore particularly efficient;

-to discover, thanks to the machine, which data have an impact on the performance of the supply chain: the theoretical approach acquired as a professional is not always sufficient to detect and explain certain phenomena that can affect the efficiency of a warehouse. Capable of identifying even weak signals, in real-time and continuously, the machine then represents a powerful vector for analyzing operations, and therefore for improving processes.

In both cases, the machine is used to establish the diagnosis, while the human being intervenes in the exploitation of the data and the definition of the actions to be implemented as a consequence.

Reinforcement learning

Mainly used by voice or banking assistants and robotics, these algorithms work on cycles of experience and improve their performance at each iteration. This is the most advanced mode of collaboration between human and machine. Through a scoring principle, the human gradually teaches the system to make the best decisions. It transfers its experience to the system and teaches it to adapt to many different situations.

Data Science is a magnificent opportunity for the Supply Chain. It is as much about gaining efficiency, reducing processing times and operational costs, as it is about acquiring a better reactivity in case of hazards, or being able to satisfy the demands of the consumers. However, it is important to keep in mind that Data Science cannot work without humans. Indeed, it is the human being who transmits the intelligence necessary to the development of AI algorithms.

This article originally appeared on GenerixGroup.com. Republished with permission.

Proper warehouse management depends, above all, on the optimal organization and coordination of stakeholders and processes. Storage is particularly important in this framework. What are the strategies and reasoning for storing in warehouses? How do algorithms save time and increase efficiency?

Using algorithms in Generix’s Warehouse Management Systems

WMS operation is based on the intensive use of algorithms. However, this is different from what is practiced with artificial intelligence, where popularity fuels the debate around calculation transparency and explainability.

We could distinguish the classical use of algorithms by the modus operandi, which is based on multi-criterion research that could be described as discriminatory or arborescent. It is separated from the use of AI tools that allow for more flexible optimal calculations.

With the Data Lab team, Generix favors the use of AI tools for very complex subjects with a large number of variables, or for in-depth analysis of Business Intelligence, such as productivity statistics, for example.

Coupled with powerful visualization tools, they facilitate analysis and decision making, as is the case with our Data Lab. However, in the majority of cases handled by a WMS, the “classic” method provides total satisfaction.

Following these explanations, we can now present the first article of a new series: an opportunity to take a look at some WMS features involving algorithmic calculations.

The logic behind warehouse storage optimization

As soon as they are received, products of any kind can be stored in multiple locations within the warehouse. There are usually several types of storage zones: racks for full pallets of different size and weight capacities, slots for cardboard box storage, alveolus cells for unit storage prior to collection… Everything is offered as manual or mechanized options, and available in multiple variants.

For each of the above categories in a warehouse, there is a geographical distribution of locations, with varying ease of accessibility.

When setting up the WMS, each location can be assigned criteria that will define their accessibility, the types of preparations allowed and their inclusion in preparation circuits. Collectively, we will work on product categorization based on the many characteristics available in the repository (basic data or “Master Data”): physical characteristics, type of packaging, product family, turnover rate, etc.

Site Reliability Engineering (SRE)

The role of the WMS will be to process all this information and then calculate the best way to store it. To do so, we’ll use a storage strategy based on an algorithm – This is the Site Reliability Engineering (SRE).

This algorithm optimizes the way products are stored based on criteria chosen among those mentioned above. A setting will then allow one criterion to be used over another, and to prioritize certain ones depending on the desired end goal.

Ultimately, optimization consists of storing products in a convenient location for order preparation, the most time-consuming operation of the process. High-rotation products will therefore be placed as close as possible to packing stations, or shipping docks, depending on the case.

This will often be done by relying on the rate of stock turnover (the speed at which a product is renewed in the warehouse). This is known as an “ABC strategy“: “A” refers to high-rotation products, and “C” to dust-taking products, also known as “slow movers”. Storage can be done according to the ABC classification as a priority, and then pair with other criteria depending on the setting chosen.

Scattering

The WMS also offers the possibility of working with a scattering algorithm, which allows products to be distributed across different aisles rather than filling one zone completely with a single item. This strategy is used when an item arrives in mass and is destined for quick distribution.

This helps avoid heavy traffic amongst forklift operators in a given aisle during preparation!

Storage close to “picking”

Another commonly used choice: storage close to “picking.” When sampling a pallet from a bottom level, an algorithm is used to preferentially store reserve pallets just above it and next to the sampling locations of the same item. The key is: even shorter resupply missions.

Warehouse Management Systems have a multifaceted role in warehouses. By collecting, processing and analyzing flow information, it allows managers to improve performance. Coupled with algorithms, WMS goes even further in automating certain storage tasks, particularly via its storage strategies.

_________________________________________________________