Can AI Be Used to Forecast Change with MLPESTEL?
Dr Khalid Alnajjar and Dr Mika Hämäläinen explored in their MBA thesis the capability of artificial intelligence (AI) to forecast change in the operational environment of companies. For this task, they employed a large language model (LLM) and developed a new theoretical framework called MLPESTEL. The Paradigm Shift that Made Forecasting Possible Traditionally, machine learning (ML) techniques have relied on learning patterns form data for individual tasks. Therefore, such models have been able to formulate predictions only in a very limited application area such as weather forecasting or financial forecasting. However, the dawn of LLMs made it possible for AI to conduct reasoning in domains outside of narrow topics and on textual data instead of numerical data. A Call for a New Framework Although LLMs such as ChatGPT have incredible capabilities in terms of reasoning and answering a variety of prompts, they cannot tackle such a difficult problem as forecasting change by a mere prompt. LLMs can reason, but they need to be given the tools to do so - just like us humans. Furthermore, such a complex task must be split into smaller subproblems. The MLPESTEL framework by Alnajjar & Hämäläinen (2024) The researchers elaborated a new framework called MLPESTEL, which draws its inspiration from PESTEL, a framework traditionally used in business research, and the Ecological Systems Theory, a framework commonly used to understand social development of a child. The former framework is important for the business application area of the research whereas the latter was used to divide each individual PESTEL category into four different subsystems – micro, exo, meso and macro systems. The resulting framework was quite complex for a person to conduct analysis with, but not at all too demanding for an LLM which can easily operate on such a level of complexity. Early Results on AI-based Forecasting The researchers investigated the viability of their method by studying the predictive capabilities of an LLM using the MLPESTEL framework on two international companies: Nokia and Tesla. The method was able to correctly predict the opportunity 5G technology brought to Nokia and the difficulties of global chip shortage that impacted Tesla. The results obtained in the thesis work are promising and serve as a proof of concept. LLMs have reached such a maturity level that they can be used in forecasting tasks. MLPESTEL has extended the theoretical capability of conducting forecasting in the context of operational business environment. This research has paved the road for future studies on LLM-driven forecasting and futures studies. The findings serve as a stepping stone for a more comprehensive platform to be developed at Metropolia University of Applied Sciences.
How AI Can Create Healthier Workplaces (Metropolia at Junction)
Workplaces are built on communication, yet miscommunication is one of the most common and harmful issues faced by organizations today. A lack of transparency can leave employees feeling unheard, while managers struggle to address issues they may not even know exist. This disconnect can lead to frustration, poor mental health, and reduced productivity. At Junction 2024, Europe’s largest hackathon, our team of four from Metropolia's Strategy and Development Services set out to solve this problem with a simple question: What if AI could help make workplaces healthier by bridging communication gaps? With Bubble Burster, we're not just solving communication gaps—we're building workplaces where every voice matters and every issue drives meaningful change Our hackathon idea was an AI tool called Bubble Burster. A platform that combines artificial intelligence, transparency, and actionability to create better communication and well-being in organizations. Miscommunication Hurts Everyone Communication isn’t just about meetings and memos. It’s the thread that ties together an organization’s culture, goals, and mental well-being. But when employees feel unheard or when managers lack visibility into issues, the thread frays. This is how AI could help people understand each other A 2022 study by the World Health Organization (WHO) revealed that poor communication, unresolved conflicts, and lack of employee support are among the leading risks to mental health at work. These risks often go unnoticed because employees hesitate to speak up, or their concerns get buried under vague processes. Bubble Burster as an AI Problem-Solver Bubble Burster empowers both employees and managers by turning communication issues into actionable insights. It works in three core ways: 1. For Employees: A Voice That’s Heard Employees can manually submit workplace concerns or rely on our AI to detect issues automatically. By analyzing virtual meetings and team conversations, the AI raises tickets for potential problems (ranging from excessive workload to workplace harassment) based on guidelines from WHO’s "Risks to Mental Health at Work." Tickets ensure transparency, giving employees confidence that their concerns are visible to managers. The ticketing system serves as a central hub where managers can monitor progress, update statuses, and resolve concerns in real time. The platform doesn’t stop there; employees receive tailored advice powered by an AI chatbot, helping them navigate workplace challenges. The chatbot provides tailored advice to help them navigate their workplace concerns, offering immediate guidance while they wait for management to take action. Figure 2: Daily diary and issue progress tracker 2. For Managers: Clarity and Action Managers rely on clear, actionable data to address workplace issues effectively. Bubble Burster’s ticketing system transforms employee concerns into structured tickets categorized by type, frequency, and department. The AI automatically classifies each ticket, allowing managers to prioritize the most pressing issues and track their resolution in real time. The well-being dashboard provides an overview of company-wide and department-specific trends, empowering managers to identify patterns, allocate resources, and make informed decisions. From acknowledging new issues to resolving ongoing concerns, the system ensures every problem is visible and actionable. Figure 3: Issues list 3. The Bigger Picture: A Healthier Workplace A healthier workplace is achieved by using data, not just non-actionable noise. Bubble Burster provides a well-being dashboard that organizes issues by department, allowing managers to track current employee’s mental health status, and process effectively. Figure 4: Company health represented in dashboards Our Hackathon Journey Bubble Burster was created during Junction 2024, a 48-hour sprint that challenged us to think fast, code faster, and build something impactful. Over two days and more than 15 hours of coding per day, our team transformed an ambitious idea into a working prototype by leveraging AI into the workplace. Representing Metropolia's Strategy and Development Services, where we specialize in applying AI to solve real-world problems, we brought together our expertise in AI and workplace dynamics. Just as we’ve worked to bring AI closer to teachers through our AI-powered Moodle plugin, we aimed to make AI a valuable tool for improving communication and well-being in organizations. The collaboration between Mika Hämäläinen, Leo Huovinen, Lev Kharlashkin, and Melany Macías, showcased the power of teamwork under pressure. By combining our skills and experience, we built a platform that has the potential to create healthier, more transparent workplaces. Why Bubble Burster Matters Our goal with Bubble Burster isn’t just to solve communication problems—it’s to create a healthier, more transparent workplace where employees feel valued, and managers can take meaningful action. By leveraging AI, we have built a system that: Detects problems employees may not voice themselves. Provides actionable data and advice for both employees and managers. Fosters trust, accountability, and well-being across teams. We hope Bubble Burster inspires organizations to view communication as a cornerstone of mental health and productivity, and this is just the beginning. As we refine the platform, we envision deeper integrations with tools like Slack, Teams, and Zoom, making it even easier for organizations to adopt. By expanding its capabilities, we aim to create workplaces where everyone feels heard, supported, and empowered.
AI research on languages related to Finnish was presented at Metropolia
The 9th International Workshop on Computational Linguistics for Uralic Languages, or more familiarly IWCLUL, was held at Metropolia. The event brought a large group of international researchers to the Arabia campus, where they presented their language technology research related to Uralic languages, which are languages related to Finnish. The challenge of being endangered Of the Uralic languages, only Finnish, Estonian and Hungarian are majority languages with official state support. The other Uralic languages are more or less endangered. The number of speakers varies from Meadow Mari with 360,000 speakers and Erzya with 300,000 speakers, to Skolt Sámi with 300 speakers and Ume Sámi with just 5 speakers. Some languages no longer have native speakers at all. However, hope is not lost even for these languages, as Valts Ernštreits, the director of the Livonian Institute, often remarks: "Every time the last speaker of Livonian is believed to have died, a new last speaker emerges from some cottage." Jack Rueter reminded us of the importance of popular culture also in the context of endangered languages. Modern language technology requires a lot of data, which makes AI development for smaller languages more challenging. Often, there is little to no data available, and it tends to have significant variation. Spelling rules are often not as clearly defined or deeply ingrained in the speakers’ habits as they are for major languages. Large language models sparked discussion. Large language models like ChatGPT do not currently support any small Uralic language. However, researchers have devised methods to elicit responses from these models by carefully crafting prompts. In addition to my own presentation, both Flammie Pirinen and Niko Partanen reported the results of their research. IWCLUL was organized through volunteer efforts. In the picture, Lev Kharlashkin is inviting the next speaker to the stage. The problem with large language models, even for Finnish, Estonian and Hungarian, is that they split words into smaller units, tokens, based on the English language. Iaroslav Chelombitko and Aleksei Dorkin had proposed solutions for this issue. Metropolia's values on display The work done at Metropolia in the fields of sustainable development and artificial intelligence was also highlighted at the event. Melany Macías presented our research, in which AI learns to predict sustainable development goals in Finnish based on English-language data. Melany Macías presented the accuracy of predicting sustainable development goals.
- How Metropolia software students worked with hardware and AI and made it to the top 5 of Finland’s largest defense hackathon
- Artificial intelligence requires continuous renewal of one’s own thinking
- Metropolia’s AI research strongly featured in an international workshop
- Metropolia Develops AI Solutions for Internal Needs
- Metropolia AI at Pedaforum 2025: Demos, Dialogue and a Lot of Excitement