Home Case Studies Baking in AI and analytics to meet rising demand Baking in AI and analytics to meet rising demand
AI helps Finnish bakery company improve planning and forecasting
Baker carrying loaves of bread on a tray

Bread is life. Each day in Finland and the Baltic region, thousands of people go to their local grocery to pick up a freshly baked loaf of Finland’s most popular bread, Vaasan Ruispalat.

For Vaasan Ltd., a 172-year-old Finnish baker that is part of Sweden’s Lantmännen Group, the production cycle is short and demanding. Its ovens must produce and deliver thousands of loaves of bread and other baked goods across the region every day except Sunday. No overstock and no shortages are allowed, and the competition is fierce.

In today’s saturated market, precise planning and automation are critical to success. No one knows that better than Joonas Alasaari, Senior Business Controller at Vaasan. “We have to be really careful about our production costs,” he says. “And we have to understand both short and long term where our capacity is heading.”

 

Huge Demand Spikes

 

To meet COVID-19 pandemic demand spikes, Vaasan supplied bread to 3000 grocery stores every day except Sunday

Better Forecasting

 

Better energy consumption forecasting improves ability to negotiate energy prices

We knew we were completely in control of the numbers. We could give them quite exact figures as to the maximum capacity and kilos we could provide to meet the spike in demand during the early days of COVID-19. Joonas Alasaari Senior Business Controller Vaasan Ltd.

In general, Vaasan has a great grasp on short-term capacity planning, since demand rarely changes, and its planning systems also account for seasonal fluctuations. But could the bakery respond adequately when the COVID-19 pandemic sent demand skyrocketing for staple products of all kinds, including bread?

“For 10 or 15 years we’ve been trying to get our production capacity as close as possible to our actual normal volumes, and then in one night we had double and triple orders from our bakery customers,” says Alasaari. “We had to answer them right away and let them know how much we could actually deliver.”

AI-infused planning and financial reviews

Vaasan has been investing in automation and planning solutions for several years. With the help of its trusted advisor, IBM Business Partner Intito Finland, Vaasan has come to rely on the IBM® Planning Analytics and IBM Cognos® Analytics solutions to simplify and expedite its business planning and reporting processes. The solutions allow the business to perform budgeting, forecasting and other financial processes in one place across the organization.

“We’ve been working with Vaasan step by step,” says Petri Sipola, Chief Executive Officer and Senior Advisor at Intito. “They had a very strong sales and operations planning culture in the company. They also wanted to see how their operations plans could correlate with finance planning. So, bit by bit, this solution has received more capabilities and become more robust. IBM Planning Analytics supports their processes, unlike some solutions where the solution would require compromises to the process.”

Today, Vaasan uses the built-in predictive, AI-powered algorithms of Planning Analytics in three critical areas of the business: predicting energy consumption and pricing, analyzing cost center trends and long-term product planning.

Using Planning Analytics to predict energy consumption helps the company better plan for and negotiate energy prices with producers. The algorithm factors in external inputs like expected outside temperatures along with production estimates. This gives Vaasan a more accurate view of its future energy needs, which it then uses to create future buying agreements with producers and purchase more sustainable energy sources. Previously, rough monthly estimates were produced manually and added little value to the company.

Vaasan also uses Planning Analytics to analyze cost center trends. Working within a four-hour window to close the books at the end of each month, the finance team could not manually review every item. Now, the solution automatically reviews the monthly reports, compares them to historic trends and flags any outliers or anomalies for immediate follow up.

Finally, Vaasan and Intito developed a long-term planning model that uses historic performance data to predict future sales. The company compares these AI-driven estimates to those drawn up by sales planners to manage overly optimistic projections if a product’s sales start to decline.

 

We are pursuing automation because we have good people. We want them to look to the future and not have to do some manual, tedious job if we can automate it. Joonas Alasaari Senior Business Controller Vaasan Ltd.
Preparing for today and tomorrow

When Vaasan needed to react to the spike in demand for its products at the beginning of the COVID-19 pandemic, it realized that it already had the right tools in place. “We knew we were completely in control of the numbers,” says Alasaari.

Once the company determined how many of the orders were actual demand and not simply a response to panicked bakery customers, it plugged the numbers into Planning Analytics. Vaasan was quickly able to reassure the bakeries that it could continue to deliver its products. “We could give them quite exact figures as to the maximum capacity and kilos we could provide to meet the spike in demand during the early days of COVID-19,” says Alasaari.

More typically, Vaasan uses IBM Planning Analytics for monthly financial planning and to create projections for the current and coming fiscal years. The solution incorporates specific, real-time and historical data about current supply, demand and external economic factors. As a result, the company can continue to reduce excess capacity and offer the product mix that customers demand.

Vaasan has a deep and wide data repository, which includes the historical energy usage data used by the Planning Analytics solution to predict energy usage. More accurate projected energy consumption will help the company further refine the financial planning process. “Now we have quite accurate estimates about both our energy consumption and energy prices,” says Alasaari. “These go into our profit and loss (P&L) for the future months, and we know what our energy cost will be six or eight months from now based on the volumes we expect to produce.”

Creating accurate energy consumption forecasts used to be a long, tedious manual task, made more complicated by the fact that the company operates across multiple countries and must purchase energy from multiple providers. Vaasan supports automating these mundane, manual tasks that the Planning Analytics solution can do more quickly and more accurately.

“We are pursuing automation because we have good people,” says Alasaari. “They are smart people, wise people. We want them to look to the future and not have to do some manual, tedious job if we can automate it.” The Planning Analytics solution can do it, in Alasaari’s words, “faster, cheaper and with better accuracy.”

When talking speed, the cost center analysis module implementation took only a few weeks to fully implement and test. “The installation and implementation were done super-fast by using the REST API from the Planning Analytics solution,” says Sipola. The cost center module is a prebuilt package that can run on any platform, including IBM Watson® Studio software, extending the capabilities of the Planning Analytics solution.

Alasaari hopes to expand the use of the cost center analytics module to other areas of the business, including flagging anomalies in daily orders. “If we see that a customer usually orders hamburger and hot dog rolls from us every Wednesday, but the order is missing this week, we can investigate whether the customer forgot the order, if it is stuck somewhere in the process, or something else has happened.” This could improve customer satisfaction and help reduce product shortfalls.

Vaasan has taken a module-by-module approach to extending planning and analysis and using Planning Analytics solution across their entire organization. As each implementation proves its value, the company moves on to the next. Its relationship with Intito is central to this ongoing strategy. As Sipola states, “It’s really nice for us that we have been able to build this trust relationship so that we are an extension of Vaasan organization.”

Because Intito is a valued IBM Business Partner, it can bring the newest functionality to Vaasan. “We get to pilot exciting and new fun stuff, so it’s a mutual benefit,” concludes Sipola.

Vaasan logo
About Vaasan About Intito Finland

Headquartered in Helsinki, Finland, Vaasan has been baking bread and other baked goods since 1849. The Finnish bakery also operates in the Baltic countries, delivering fresh bread and confections to more than 3,000 shops every day. Vasaan has approximately 1,400 employees in Finland, Estonia, Latvia and Lithuania, and is part of Lantmännen, a Swedish agricultural cooperative and Northern Europe’s leader in agriculture, machinery, bioenergy and food products.

About Intito Finland

IBM Business Partner Intito was founded in 2014 with a mission to build planning solutions that help businesses make better decisions by automating processes. The company, based in Helsinki, Finland, provides full-service solutions from design to implementation and continuous support to its customers.

Next up:
How a bakery company used AI to upgrade planning Vasaan Ltd. blog Deep operational insights drive better decision-making Continental Foods case study Faster, better planning during turbulent change Novolex case study
Footnotes

© Copyright IBM Corporation 2022. IBM Corporation, IBM Security, New Orchard Road, Armonk, NY 10504

Produced in the United States of America, January 2022.

IBM, the IBM logo, ibm.com, Cognos, IBM Watson, and with Watson are trademarks of International Business Machines Corp., registered in many jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on the web at “Copyright and trademark information” at https://www.ibm.com/legal/copytrade.

This document is current as of the initial date of publication and may be changed by IBM at any time. IBM Business Partners set their own prices, which may vary. Not all offerings are available in every country in which IBM operates.

The performance data and client examples cited are presented for illustrative purposes only. Actual performance results may vary depending on specific configurations and operating conditions. THE INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS” WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided.