Our optimization AI crunches large-scale instances with billions of variables.
We take care of availability and scale in software as a service deployments; we also support on premise installations.
We help our clients in business analysis and modeling of their decision-making challenges.
Do you have an ongoing painpoint with planning your resources efficiently and accurately? Planning is timeconsuming, expensive and subject to errors? Then an optimizer based on decision AI is the right solution for you. It is a software that produces automatic, algorithmic decision support for your planners at the rules that apply to your company. We are experts in the field.
Together, we analyze the requirements to solve your use-case.
We configure our decision AI models and deliver a minimal lovable optimizer.
The solution is tested, validated, and iterated with your domain experts.
We operate your solution, reducing your effort and improving your ROI.
We are ready to tackle it.
Alexander Souza is the founder and CEO of Algomia. He has many years of professional experience in the optimization and software industry. He holds a doctorate degree from the ETH Zurich and holds a lectureship on algorithms at the University of Zurich.
Our customer - a top-tier national passenger rail company - wants to organize all its 12'000+ daily train legs into as few as possible shifts for its 70 crew depots. Of course, shift consistencies, labor rules, crew qualifications, etc. must be fulfilled. Creating a planning solution manually means a multi-month effort of a dedicated team.
We created a decision AI model with 1.3+ billion variables. Of course, all required constraints, labor rules, skill-requirement, and consistencies are captured.
Our AI algorithms solve the model within only 43h of compute time with provable optimality guarantee of 1.9%.
Our Decision AI algorithm reduces the overall FTE count by an undisclosed, but significant amount, translating to a substancial savings potential.
This was a substantial breakthrough, since the methods applied previously did not scale accordingly. This opens new strategic opportunities, e.g., large-scale simulations.
The economic efficiency of railway companies depends, among other things, on the optimal use of human resources. However, disposition is complex: shifts must be planned not only according to rest times and absences, but also according to qualifications, route knowledge and locomotive expertise.
The new AI optimizer for staff scheduling in zedas®cargo Long Haul significantly simplifies a time consuming processes in rail freight transport. Duty rosters that previously took up to two days to prepare can now be generated fully automatically – in just a few minutes.
The software takes all relevant factors into account: qualifications, rest periods, absences and travel times from home or hotel to the place of duty. At the touch of a button, ready-to-use schedules are created that automatically take qualifications, rest times and absences into account. The result: over 90% time savings, fewer non-productive transfers, significantly reduced overtime costs and a noticeable boost in productivity. At the same time, the planners' experience can be mapped directly in the system – for sustainable, reproducible results.
In addition, the software also optimises so-called guest trips – i.e. the journey from home or hotel to the job site. The result: less overtime, higher productivity and lower costs.
The contracted warehouse struggled with time-consuming pick-and-pack processes and inefficient routes. Historical data from thousands of past orders showed the scale of lost productivity—but also held the key to change.
By integrating Algomia’s advanced routing optimization model, the customer was able to harness this vast order history. The AI engine mapped every aisle, product, and order pattern, then generated optimized routes that perfectly fit the unique operations.
The results were extraordinary: The customer achieved a 30% reduction in pick-and-pack path lengths across the team. Orders went out faster, customers got their products sooner, and operational KPIs took a significant leap.
Our flow-based solver for large-scale combinatorial optimization is a breakthrough technology, empowering industries to solve the most complex optimization problems rapidly and accurately. Purpose-built for scalability, versatility, and consistent high-quality results, this solver transforms the way large-scale allocation, scheduling, and planning challenges are addressed in real-world environments.