The Quantitative Supply Chain

For a supply chain management practice to be performant, managers need to have access to the position of every single asset. Unlike classic electronic inventory management, Internet-of-Things (IoT) offers the possibility to gain real-time visibility on all assets, vehicles included.

Properly preparing the data is a requirement to achieve success for any data-driven initiative. When considering supply chain challenges, data preparation is difficult because it involves complex enterprise systems that have not been designed with data science in mind.

A free market is not only about competition, cooperation matters too. Cartels have a role to play in Bitcoin and supply chains alike.

Forecasting promotional demand is necessary in order to allocate the correct amount of stock. However, time-series forecasting models are typically not a good fit to address pricing-related demand patterns. More complex machine learning forecasting models are needed to properly take into account past promotions, and to reflect the upcoming impact of those that are planned.

Supply Chain Management (SCM) systems feature complex user interfaces. Among them, demand forecasting subsytems are not only complex but complicated as well. Better user inferfaces are needed to tackle this complexity.

Modern supply chains are complex, and the most direct answer to complexity is a 'specialization of labor'. Unfortunately, this approach results in 'silos' that fail at delivering decisions that maximize returns for the company.

Supply chain challenges are frequently quantitative and data driven. This makes them a good fit for a data science practice. However, understanding the business is a frequently overlooked aspect of the data science practice in supply chain.

Blockchains and Bitcoin do have applications for supply chains, but not the ones most prominently put forward by software vendors.

Artificial Intelligence (AI) is an umbrella term that covers many high-dimensional statistical methods such as Deep Learning or Differentiable Programming. These methods can be used in various ways to improve the operational performance of supply chains. However, both problems and solutions differ vastly from mainstream AI problems such as Natural Language Processing (NLP).

More accurate forecasts are expected to yield better supply chain performance, but it's not always the case.