A quick overview of recent customer case studies involving the application of Microsoft’s AI, Big Data & Machine Learning offerings.
Carnival Maritime Predicts Water Consumption on Cruise Ships
The Costa Group’s fleet of 26 cruise ships sail all over the world. The industrial equipment on their ships have thousands of sensors that collect data in real time. As part of their digital transformation, the company’s marine service unit, Carnival Maritime, wanted to explore how it might take advantage of this data to find opportunities for operational improvement. One of the areas they looked at was that of water consumption onboard their ship. This is a complex problem, as consumption patterns can vary widely. Passengers of different nationalities shower for different durations at different temperatures and times of the day, for instance, and there are numerous other variables that make such consumption challenging to predict. Accurately predicting water consumption helps ship captains avoid the need to spend fuel by unnecessarily producing excessive amounts of water at sea. This also mitigates their need to carry all that excess water along the way, which further shaves costs.
Carnival needed a mechanism to predict the right amount of water to produce at the right time, without having to store any excess. Carnival’s partner, Arundo Analytics, a global provider of analytical and predictive solutions, helped them build a microservice on their proprietary big-data platform, and trained a model to help them do just that. Using the machine learning models, APIs, and templates in the MICROSOFT CORTANA INTELLIGENCE SUITE, Arundo analyzed historical data sets along with data such as the speed and position of the ships, age and nationality of passengers, historical weather data and more, to better understand exactly the drivers of water consumption. Their platform runs on Azure and is able to easily connect to and derive value from a variety of data, and from both Carnival’s cloud and on-premises databases.
Carnival is now able to better predict how much water a ship will need for a specific route with a particular set of guests. They estimate that their optimizations can help each ship save over $200,000 a year. The solution also contributes to the company’s goal of reducing carbon emissions. Carnival is next looking to implement a predictive maintenance solution for its fleet, using Cortana Intelligence to study the data that’s already being collected from thousands of on-board sensors on each ship. You can LEARN MORE ABOUT THE CARNIVAL MARITIME STORY HERE.
Arçelik A.Ş. Increases Forecasting Accuracy on Spare Parts
ARÇELIK A.Ş. manufactures and sells a range of appliances, including televisions, air conditioners and major kitchen appliances, and owns many popular brands such as Grundig. They are a leader in most of the 135 countries in which they operate, and owe much of their success to post-sales customer service.
Since Arçelik A.Ş. sells thousands of product SKUs and maintains an inventory of hundreds of thousands of spare-parts to service them, getting the right spare parts to the right place at the right time is the key to getting their customers back up and running quickly with their products. But with a catalog of 350,000 spare parts that was growing a further 10 percent each year, Arçelik A.Ş. found it increasingly hard to accurately forecast the parts they needed across all the markets they serve. They had many different systems for data collection, sometimes even relying on spreadsheets that were being managed by hand. Their old system simply wouldn’t scale or help them achieve their goals of maximizing customer satisfaction while minimizing inventory cost.
To address this situation, Arçelik A.Ş. decided to invest in a spare-parts demand forecasting built on Cortana Intelligence. With the help of solution provider BilgeAdam, they made their first move to the public cloud with this solution. Their decision started delivering benefits even before the impact on inventory management could be felt. For starters, the company went live with the solution in just three months, whereas they had anticipated an 18-month development schedule based on an earlier solution. They also got a highly scalable solution, thanks to their cloud bet, and one that’s much easier to integrate with external data sources such as weather or location, to enhance their forecasts. Furthermore, they avoided expensive investments in IT infrastructure and personnel that would have been needed to build and maintain their alternative solution.
Here’s how the solution works: Spare-parts demand data is uploaded into AZURE SQL DATABASE. Next, AZURE MACHINE LEARNING is used to test four algorithms, to identify the most accurate one, based on the current data set. That algorithm is then used to forecast their spare parts needs for the next 12 months out. The subsequent month, the solution updates the data set, and the same experimenting and forecasting process is repeated. The testing process is automated using AZURE DATA FACTORY and their algorithms are based, in part, on time-series R code developed for Arçelik A.Ş. by BilgeAdam.
The result is a much more accurate and useful forecast that’s also speedier and easier for Arçelik A.Ş. to generate. Their 12-month forecasts, which used to take 2-3 weeks to produce, are now generated every week. What’s more, these forecasts cover three times as many SKUs as their earlier solution. With forecasting accuracy already up to 80 percent (from the earlier 60 percent) and inventory turnover expected to climb by 10 percent, service calls are getting made faster and more cost-effectively, and – most important of all – Arçelik A.Ş. customers are much happier. You can click here to LEARN MORE ABOUT THE ARÇELIK A.Ş. SOLUTION.
Mars Drinks Creates Smarter Vending Machines
MARS DRINKS is a pioneer in supporting companies that want to provide great working environments for their people. In 1973, they introduced the first-ever fully automatic in-cup drinks vending machine, serving large manufacturing channels across Europe. In 1984, they introduced the first system for making hot drinks using fresh ground coffee and leaf teas sealed in individual servings. Mars Drinks’ solutions support hassle-free solutions for workplaces, delivering on taste and choice and with a commitment to sustainability.
To deliver the best possible service to its wide array of customers, ranging from consumers and businesses to distributors, Mars Drinks needed the ability to better anticipate and manage stock levels across their machines, which are distributed throughout the globe. Working with Microsoft partner Neal Analytics, they were able to apply machine learning to their vending machines. Tapping into the data they gather from remote sensors on their vending machines, and coto the MICROSOFT AZURE IOT SUITE, Cortana Intelligence and POWER BI, Mars Drinks is able to use and predictive computing to better maintain stock levels, understand consumer behaviors and account for changes in demand related to factors such as weather and holidays.
For Mars Drinks’ distributors, who are subject to a fine each time a product is out of stock, this ability to better anticipate and manage stock levels will enable them to avoid unnecessary revenue losses.
CIML Blog Team