Az NKFI Alapból megvalósuló program

Dorsum is proud to benefit from the European Commission's Brexit Adjustment Reserve.
Learn more about our project aimed at aligning our Wealth Management Suite to the UK market.
(Hungarian content)

Recommendation Engines – Machines That Want to Know Everything About Us

Kattintson ide a magyar verzióért.

Surely many of us have had the feeling when browsing through recommendations on the web that the system can read our mind. It is almost terrifying how well some of these online recommendation engines have gotten to know us, be it the ones used by YouTube, Netflix or certain online marketplaces. This is no coincidence, since the technology that sits behind these solutions is rapidly evolving. But what do we mean by “recommendation engine” precisely? 

Recommendation engines are software that make personalized recommendations based on the data fed to them. This data can be any information about our behavior and preferences, such as our search history, the device we are browsing on, our geolocation, our online interactions, or more personal information such as our age or gender. Nowadays it is almost impossible to avoid recommendation software while browsing the Internet as they are now an essential part of social media, online entertainment and e-commerce, and in recent years they have started conquering the investment management industry. 

In our current blog post, we first look at how recommendation engines are utilized in the world of investments, then we proudly present our own investment recommendation engine developed here, at Dorsum. Let’s dive in! 

It comes as no surprise that the “hyper personalization” achieved through the use of recommendation engines had made it to the world of investments. If these solutions are able to generate product recommendations from our browsing habits or movie recommendations from our viewing habits, why couldn’t we use them to provide investment recommendations by looking at financial behavior? The recipe is the same: products and services are recommended to users based on information gathered from large data sets using algorithms. The main difference is that in the case of investments, data sets consist of financial and capital market data that are used to recommend investment products and services. We should note that this required financial institutions to start storing and organizing these already available data in a way that makes them easily processible by recommendation systems. 

When recommending investment products, however, we cannot just copy the general formula used in e-commerce due to the unique features of the market. Because while the logic behind the two is basically the same, the characteristics and environment of the recommended products are very different. For example, clients of financial institutions do not rate products explicitly. Plus, certain characteristics of financial products (e.g., the price of stocks) might change radically from one minute to the next which can have a huge financial impact on investors. Which is entirely different from buying a shoe for example, where we can leave a customer rating that is actually relevant, as the next customer will buy the same product in (mostly) the same condition. The price of the product won’t plummet either after a negative comment. 

Due to these features, a client’s risk profile and their investment objectives (MiFID), for example, are crucial pieces of information for accurate investment-related recommendations. Then, investors are profiled based on past transactions or certain traits and characteristics (e.g., social and psychological factors). Finally, we can further refine these recommendations with the use of AI technology, which seems to have become a staple in cutting edge recommendation engine software, since it is surprisingly good at uncovering personality traits and characteristics that we do not perceive as outside observers. 

Dorsum’s Recommendation Engine is also a sophisticated, AI-based investment recommendation solution. It uses a form of deep learning AI technology called a “neural network”, which is a hardware- or software-implemented information processing system that is capable of parallel, distributed operation. It consists of an interconnected network of neurons (processing elements) modeled after those of the human brain. It has a learning algorithm, and a retrieval algorithm that utilizes the learned information. 

Recommendation Engine has the ability to learn what instruments can be recommended to investors by organizing them into groups based on patterns it reveals in data sets consisting of historical transactions and other customer data, practically creating its own ruleset. This is called the learning phase. The retrieval phase typically takes much less time, during which the data of a customer is analyzed against the patterns learned by the system. At the end of the retrieval phase, it outputs the set of investment products that fit the client’s profile and can be recommended to them. 

A so-called preprocess is carried out before data is fed to the neural network. We can think of this as pre-filtering: we can tell the system to ignore certain information (e.g., if we know beforehand that the residents of Budapest do not conform to the pattern), or we can pre-define groups (e.g., we can separate metropolitan, city, small-town, rural etc. residents). 

An additional postprocess allows for data manipulation after the data has been processed by the neural network. In doing so, we can influence the results so that they align with business or marketing decisions. We can change the weighting of a particular product, increasing its chances of being among the recommended set of products or we can even fix certain products to make sure they are included in the final recommendation. 

The potential behind Recommendation Engine is nigh impossible to assess, as the accuracy of recommendations can in theory be increased indefinitely by carrying out learning processes on new data sets or by fine-tuning the operating parameters. Improving data quality should also increase efficiency, and even new types of data may appear in the future that are not currently available or do not exist. 

AI-based systems are without a doubt still in their infancy, but it is already clear that they will have a huge impact on the future of humanity. With Recommendation Engine we want to be a part of this breakthrough and bring the technology to the investment market. 

Dorsum is committed to further R&D on the future of profiling and recommendation engines as part of tender 018-1.3.1-VKE-2018-00007 „Automated and verified evaluation and categorisation of financial products and service providers for secure, personalised investment services”.

Share this article

RELEATED ARTICLES

  • All
  • blockchain
  • crypto
  • Egyéb kategória
  • ESG
  • Events
  • Insights
  • News
  • Regulation
  • Switzerland
  • UK
  • White papers

Every good business relationship starts with a single step!

Martina Bagarić Maršić

Head of Business Development CEE Region

Martina doesn’t believe in transactional sales — she builds business ecosystems based on genuine partnership. With over 15 years in the industry, she consciously steps away from aggressive tactics, championing an “ethical sales” approach instead. For her, building transparency and trust is the absolute core of any business relationship. A secret introvert, she relies on a quiet hour of morning routine to recharge her inner peace, ensuring she can give her absolute best to her clients all day.

Her superpower? 
Reading the room. She instantly decodes true needs, so clients feel like partners, not just transactions.

What won’t she do? 
Parachute jump. She will gladly help redesign your business strategy or share practical life advice, but she will never jump out of a perfectly good airplane.

Kadra Aden

Head of UK Product

Kadra started her career writing code, which means she doesn’t just manage products, she understands their DNA. As Head of UK Product, she uses this technical fluency to translate complex business needs into reality. She digs past the initial “wish list” to find the actual root problem, ensuring Dorsum builds solutions that work in the real world, not just on a whiteboard.

Her superpower? 
The Strategic “No.” She isn’t afraid to kill a weak feature to save the product vision.

What won’t she do? 
Sit still or sing. She works from a treadmill desk to keep moving, but hand her a karaoke mic, and she’ll clear the room instantly.

Hannah Buckle

Head of UK Sales

Hannah proves that high-stakes tech sales doesn’t have to be a rigid, jargon-filled grind. She brings a genuinely fun, open, and relaxed energy to the room, believing that the best partnerships start with a simple, honest chat. And while she keeps things light, she is fiercely persistent when it comes to solving business problems. Whether she is untangling a messy digital ecosystem or helping a team scale, her secret weapon is that she simply never gives up. She operates with radical honesty, zero fluff, and a commitment to keeping the process as enjoyable as it is successful.

Her superpower? 
Relentless persistence. She never gives up on a problem, bringing a fun, conversational vibe to even the toughest business challenges.

What won’t she do? 
Use clinical buzzwords. She solves complex tech puzzles daily, but happily leaves words like “diagnostic” to the Apple Store.

Szilvia Kovácsné Szántai

HR director

Szilvia has been the heart of Dorsum’s community since 2006. While her title says HR Director, she acts more like a human bridge between business logic and employee well-being. She always looks past the bullet points on a CV to find genuine curiosity and loyalty, knowing that true team spirit cannot be automated. She is the kind of leader who will boldly trade a flashy corporate party to secure comprehensive health insurance for everyone. After a week of navigating complex group dynamics, she unplugs completely, relying on time with family and friends 
as her ultimate reset button.

Her superpower? 
Reading the room. She instantly tunes into group dynamics, sensing hidden tensions in a meeting long before anyone says a word.

What won’t she do? 
Talk strategy before coffee. She never sacrifices humanity for results and refuses deep discussions before her own system boots up.

Péter Sallai

Chief Technology Officer

Péter is the kind of CTO who doesn’t just set direction—he understands and enjoys technology all the way down to its deepest layers. He believes great architecture isn’t built for fashion, but for endurance: systems should stay strong under real load and evolve as needs change. At Dorsum, he designs and leads teams building long-lasting platforms that can modernize without big-bang rewrites—stable foundations, modular components, and the mindset of being able to “swap the engine mid-flight.”
He makes strategic choices with engineering pragmatism: spotting what will remain useful versus what’s just noise, and translating complex technical topics into clear language for developers and clients alike. And he stays hands-on—when something matters, he dives in and builds.

His superpower? 
Tech Intuition + Deep Dive. He sees the big picture, but can go all the way into the details when the root cause—or the right decision—lives there.

What won’t he do? 
Predict the lottery. He will happily predict future tech trends, but please don’t ask him about the winning numbers.

Miklós Muszkuly

Chief Project Officer

Miklós began his journey at Dorsum as a trainee in 2008. After expanding his expertise at the Big Four and major banks, he returned to lead our most complex projects with the calm focus of a seasoned athlete. He knows that software is just the final output; true delivery is about providing the stability that makes clients feel completely secure. Operating on the strict philosophy that there is a massive difference between a project being “done” and functioning “well,” he never settles for the former. When project chaos hits, his grounded approach, fueled by family time and sports, ensures our partners always know they will “never walk alone.”

His superpower? 
Elite situation awareness. He instantly decodes complex dynamics, pinpointing the hidden risks and success factors of any project.

What won’t he do? 
Settle for “just working.” He strictly separates functioning from functioning well, and flat-out refuses to compromise.

Magdolna Pánczél

Country Manager

Managing two international subsidiaries requires a rare blend of adaptability and order. While Magdi naturally approaches the corporate world with the logical rigor of a Six Sigma expert, she understands that the people behind the projects are beautifully varied. She operates as a dedicated coach for her teams, patiently explaining the “why” and “how” behind a strategy rather than simply delegating tasks. After a week of successfully organizing complex international operations, she unplugs by embracing the organized chaos of family life and spontaneous weekend travels.

Her superpower? 
Contextual empathy. She instantly tunes into the unique mindset of any new client or culture, finding the exact common ground to build trust.

What won’t she do? 
Stay home on a weekend. After a highly disciplined workweek, she absolutely refuses to sit still on a Saturday.

Gábor Jandácsik

CFO & COO

With a three-decade career spanning both risk management and sales, Gábor brings a rare dual perspective to financial leadership. He approaches his role as CFO and COO much like a classic football defender: he knows the backline offers the best strategic view of the field, but he also understands that without scoring goals, the business cannot win. For him, financial modeling isn’t a tool to hold the team back, but a transparent safety net that empowers the organization to confidently chase growth. After a fast-paced day of balancing risk and reward, he relies on quiet “processing time” to mentally organize his thoughts, keeping his mind clear for genuine human connection.

His superpower? 
Stepping into your shoes. He instantly understands the real motivations of clients and colleagues without judgment.

What won’t he do? 
Walk away wearing them. He avoids unsolicited “if I were you” advice, giving you the context but leaving you the freedom to pick your own pa

Bálint Fischer

Chief Business Development Officer 

Bálint blends banking pragmatism with a builder’s curiosity. Having spent long years sitting in the client’s chair at major financial institutions, he intuitively understands the anxieties of digital transformation before they are even spoken. He is a “visionary doer” who combines a mathematician’s logic with a deep passion for connecting people, ensuring that technology serves human goals, not the other way around. Since joining Dorsum, he has been the driving force behind our international expansion and innovation. 

His superpower? 
Finding the courage to challenge “limits” that exist only in our heads. 

What won’t he do? 
Accept “because we’ve always done it this way”
as a valid answer. He is far too curious for that. 

Róbert Kő

Chairman of the Board

Robert brings the “emotional part” to the boardroom, focusing entirely on the people and trusting the experts with the professional execution. He believes that genuine trust is what carries a project to success, not just the contract. He is the one who finds cooperation even in a defeat, always looking for the positive outcome where others might see a loss.

His superpower? 
Creating balance in any conversation. He instinctively helps partners find their place in a meeting, ensuring the discussion is authentic and leads to a real connection.

What won’t he do? 
Ask “is there another way?”. He simply creates one, even if he must build the bridge himself.

Mariann Mészáros

Chief Executive Officer

Mariann brings over 25 years of enterprise discipline to Dorsum, yet she leads with a refreshing reliance on “common sense” over rigid corporate playbooks. She understands that strategy is nothing without the people who execute it, so she focuses on aligning organizational capability with business targets. For her, profitability is key, but she isn’t afraid to override the financial targets if the long-term market position demands it. She views leadership not as a solo performance, but as a shared responsibility. She strictly adheres to the motto that “no one should be a leader without empathy,”.

Her superpower? 
Balancing Strategy, Culture, and Numbers, instinctively knowing which one needs a push.

What won’t she do? 
Play the lonely hero. Lone wolves look cool in movies, but in business, they just get tired.