Is the magic of AI/ML supply chain technology real?

Arthur C. Clarke got a point when he stated that beyond a certain point technology becomes indistinguishable from magic.

AI/ML technology use and adoption in supply chain planning is still in its infancy, but the promises of such technology are already showcasing results beyond the wildest dreams of many planners, who still work in outdated applications or excel spreadsheets.

There is no debate anymore that Artificial intelligence and Machine Learning provide powerful solutions to address planning challenges.?Several used cases demonstrated a positive impact.

The challenge is to scale up and develop a large enough pool of experts to accelerate the learning curve for all of us, and increase the collective expertise in this field.

Below the 3 main used cases we see gaining momentum in the supply chain space

1. AI/ML Forecasting

Former GE exec Ian Wilson had a point when he stated that “No amount of sophistication is going to allay the fact, that all of your knowledge is about the past, and all your decisions are about the future.

Forecasts used to be based on statistical time series. The more established statistical techniques focus on basic patterns like trends or seasonality or potential correlations, the cleansing of past sales history, and the manual determination of the impact of events, that might drive a deviation of the future sales from past history.

What Ian could not foresee is the fact that a machine would become so powerful it can assess far more events and test far more input data to create a prediction in a far shorter timespan than a planner possible could, taking our human bias out of the equation and producing a better consensus forecast.

AI/ML is also much faster than planners to align opposed views and intuitive opinions from sales executives and marketing experts (we either call this gut feeling market intelligence or bias).

With AI/ML forecasting, we are talking about a significant productivity gain.

2. AI/ML Demand sensing and shaping

The most interesting predictive analytics used case is not forecasting but the correction thereof. Given a forecast is by definition wrong in a more volatile and uncertain environment, the speed to auto-correct the forecast (demand sensing) and then recommend a different response based on what is really happening in the market (demand shaping) is a super power offered by AI/ML.

Instead of slowly reflecting changes in the market with a lag and at human speed, AI/ML can continuously and intelligently scan and leverage specific data that are invisible to a planner, but are potential indicators of shifts in ordering behavior, new trends or changing market patterns.

By sensing where our demand deviates from old and outdated patterns, continuously adding new insights to the forecasts based on shopper data, shopping basket analysis, competitor price changes, logistics transactions, weather data, even such widely available data like number plate registrations, store visits, eCommerce traffic or any other valuable features, AI/ML can interpret market dynamics, then learn to influence and interact with the consumers in real-time influencing their buying behavior through contextualized pricing and promotions.

Now we are talking real magic.

3. Self-healing supply chain

The magic of AI/ML is not limited to the demand planning side. On the supply planning side, planners face a continuous challenge to keep their digital twin representation in line with the ever changing reality of their supply chain and new constraints or disruptions.

Delayed planning parameter updates across a multitude of databases, duplicated data and information prone to errors is very common in planning systems.

Using self-healing and machine-learning capability, one can continuously scan the supply network data, including complex planning parameters like leadtimes, inventory targets or yields to identify and auto-correct inconsistencies.

That's the promise of AI/ML. The combination of demand sensing, demand shaping and self-healing supply chain might sound like magic, but the capabilities are available today.

Over the past years we experienced firsthand the magic of AI/ML Supply Chain solutions, and we are ready to go mainstream!

See you in Wonderland!