Warehouse robot developed capable of collecting food

The widespread scope of the coronavirus pandemic and the need to deploy a vaccine as soon as it is ready has introduced new complexities in the global supply chain. These include the number of parties and jurisdictions involved, different levels of maturity in data analysis, and transportation and communication issues, among others.

Artificial intelligence (AI) and data analytics can provide opportunities to more accurately predict challenges and plan for a quick and efficient response while minimizing future disruptions.

The COVID-19 pandemic has highlighted new and existing problems in the supply chains of many industries. Disruptions in the supply chain of consumer goods, manufacturing and healthcare have been making headlines since the beginning of the year. Additionally, some logistics organizations are struggling to collect and analyze quality data, while bottlenecks at any link in the chain threaten to cause cascading disruptions.

This is where AI, and machine learning in particular, can help.

Artificial intelligence can refer to many implementations of the technology, but machine learning is the most important implementation of AI. Use algorithms and applications to automate data analysis and build knowledge models. Machine learning solutions can be used to perform predictive analytics, such as regression and classification analysis, which can be particularly useful for predicting business supply chain problems.

Transportation applications

Transportation problems are often a significant component of supply chain disruption. Artificial intelligence solutions can help solve these challenges by automating data collection from various points in the journey and then using advance shipping to a satellite location to meet consumer needs, sometimes even before the need is reported.

Another way to increase transport efficiency could be to allow rescheduling of deliveries and truck route changes based on the latest traffic and weather patterns. Including this data in predictive models can make those predictions more relevant and the process more efficient.

Other useful uses include forecasting inventory outages. Let’s take the example of the eventual distribution of a COVID-19 vaccine: it would be essential to foresee not only the availability in the warehouse of the vaccines themselves, but also peripheral stocks – such as syringes, diluent and refrigeration supplies. All of these factors could ultimately affect millions of lives. Forecasts related to patient care, such as staffing needs and appointment time per patient for immunization, may also become important.

A huge challenge for the supply chain

Deploying a COVID-19 vaccine will soon be the biggest supply chain challenge facing the world. To successfully deploy a vaccine, organizations may need to anticipate several aspects of the supply chain, including:

Consumption times by country, region, city and possibly vaccination location. Learning where vaccines will come from and where they will be distributed to their final destination can help simplify logistics.

Procurement, availability and cost of materials. The forecasting of shortages will be particularly important for manufacturers so that they can mitigate potential risks.

Places of production, planning and sizing of lots. Distributors will need to take into account the size and availability of storage facilities along the distribution route.

Potential for stress on quality control resources. Several quality control points will likely be required to ensure vaccine viability. Overloading these “checkpoints” would create bottlenecks in the chain.

Probability of deterioration and cascade effect. COVID-19 vaccines must be stored at controlled cold temperatures and are susceptible to spoilage if deviations occur. Modeling space allocation and anticipating problems with storage can reduce the potential for inventory waste.

The nature and scale of COVID-19 introduces long-tail risk scenarios that include more uncertainty than could help resolve previous information about implementing immunization. Many more simulations may be needed to provide examples of aligning multiple events and low-probability scenarios.

Automating data collection and transformation through the use of robotic process automation (RPA) from as many sources and organizations as can be involved in vaccine production and distribution can help reduce manual errors, speed up the process and enable analysts to make more accurate predictions.

It’s all in the data

While there are many complexities involved in every junction of a supply chain, organizations can generate significant value by making incremental efforts towards data analytics maturity, without necessarily adopting a robust machine learning solution. The value from AI capabilities and improved data analytics eventually comes in the form of better decision making in the face of uncertainty. An organization’s data can contain indicators of risk and new value opportunities. Most organizations can start by improving their data governance processes, unlocking the true potential of data.

The data for modeling can come from many sources: past and present supply and demand models, real-time traffic and weather updates, inventory data, market forecasts, etc. As with any input-output process, more accurate data input produces more accurate predictions. Improving version control and change management practices related to data management can help protect data quality. Furthermore, the assumptions gathered from this data and incorporated into the predictive models must be well documented to explain the logic and to allow continuous monitoring of the model’s performance and adjustment.

In addition to the data used to establish the models, the data for updating and adapting the models is essential. The faster reliable data can be received through the supply chain, the faster other parties can respond. In the coronavirus immunization example, data from immunization sites (such as hospitals and clinics) should be shared as efficiently and accurately as possible to allow manufacturers and logistics companies to respond accordingly.

Implementation of AI solutions

An automation specialist with experience implementing RPA solutions can help organizations identify and refine data sources from various business functions. Once relevant data and processes are identified, automation can improve the data collection process and quality.

In addition, automation solutions exist to help organizations establish standardized business logic, enabling better identification and monitoring of key performance indicators (KPIs) with the use of management dashboards and mitigating risks more quickly and competently. .

The COVID-19 pandemic may continue to have a disruptive impact on industries in the years to come, and some of the long-term implications are not yet obvious. However, good data analytics practices are available for organizations of all sizes and levels of sophistication.

Artificial intelligence, especially machine learning and automation, can help some organizations predict events and act in advance. Organizations that haven’t already done so should plan now how they will use these new technologies and the power of data to unlock potential opportunities and value, while addressing the supply chain challenges the world faces today.

Roberto Valdez is director of Cybersecurity Automation and Risk Advisory Services at Kaufman Rossinby working with companies to mitigate risk, protect their information and achieve their strategic goals. Pedro Castillo is a manager, business consulting services, at Kaufman Rossin, with expertise in performance measurement, operations improvement, goal setting, capital allocation and executive remuneration.