We deliver comprehensive, innovative solutions and consulting services for global enterprises, government agencies and public health authorities.
We are hiring the best programmers and experts in the field.
Corporate & Government
We are delivering innovative solutions for leading corporations, public health authorities and government agencies. Some of our customers are on the Fortune® 100 list.
Fraud detection on Value Added Tax.
For the Taxation Office, Cognitum implemented natural language rules enabling decision makers and specialists to manage a tax fraud knowledge base. Reasoning with AI Agents is used to recognise elaborate fraud and non-compliance patterns. A stream-based reasoner, developed by Cognitum, allows discovering fraudulent activities in the stream of 5M invoices per day.
Technology: Knowledge Representation, Knowledge Graph, OWL/RL reasoning
Automated Decision Making System
In order to sign a contract, CEO of the leading corporation has to analyse business situations and implement a good strategy, especially about 10m$+ contracts. CEO makes highly contextual and time-sensitive decisions that have to factor in priorities, such as risk aversion or profitability.
Cognitum has developed the Automated Decision-Making System. The core of the system combine both expert knowledge and intuition-graphs, in order to calculate the quality score of the deal/opportunity.
A.I. models wrapped in the user-friendly UI, with drag and drop editor for tuning the expert knowledge consumed by the models produce a visualisation of the results for the CEO.
Technology: C#, Python (JupyteR), Absorbing Markov Chains, Graph databases, OWL/RDF
Trade Promotion Optimization
Sales analysts are responsible for providing the promotion plan for the new quarter in most of big FMCG enterprises. Currently, these plans are created manually, mostly using conventional tools like Excel that try to solve the typical TPO (Trade Promotion Optimisation) problems like: promotion strategy, effective promotion calendar, optimise budget KPIs.
Cognitum combined business knowledge of subject matter experts with historical sales data that we received. We also took into account their anomalies and outliers. Thanks to that the Solution enabled the Company to perform sales analysis across multiple products categories over time and make a prediction of sales volume in a given time frame. The solution enabled the Company to increase its accuracy in prediction by up to 10% of volume planning.
Technology: Python C#, MSSQL, R (RStudio), Python (JupyteR), Django, SPA in React/Redux
Clinical Decision Supporting System for the public health authority
Clinical registers are needed to perform research studies and thus to increase medical knowledge that finds its way into new and improved guidelines. Adherence to clinical practice guidelines is mandatory to increase the effectiveness of treatments and to eliminate the negative consequences of medical decisions. We organised available data into the knowledge of the diagnostic process, based on many sources like studies, publications, recommendations, so it supports doctors decisions. We also developed a central registry for collecting patient’s clinical data from over 70 oncological institutions in Poland. In production since 2016. The results were published in Expert Systems With Applications that is currently ranked number 1 in the Google Scholar h-index listed under the top publications of Artificial Intelligence.
Technology: Python, JupyteR, C#, Jena, Knowledge Graphs, Controlled Natural Language, Ontologies, SNOMED, OWL/RL reasoning
The telecommunication company in Australia, besides being a telecommunication provider, is a solution provider of a strong, policy-driven security architecture – a B2B framework of clearly articulated security principles that can be enforced through defined security domains and controls, and implemented through set standards, guidelines and procedures.
Cognitum developed a tool, that is allowing encoding the knowledge of cyber-security expert. Then it is allowing customers to perform guided cyber-security health check, and after the health-check is completed, the detailed report (diagnosis) is generated allowing the customer to understand the current state of the company’s cybersecurity maturity level and understand the weak points. The estimation of the Potential Cost of the Problem is also provided.
Technology: Python, JupyteR, Knowledge Graphs, Controlled Natural Language, OWL/RDF
eCommerce Customer Reviews Optimization
The Company struggled with either one: overestimating or underestimating of the budget for products startup and products lifecycle management on the Polish market. Working for them, we prepared Machine Learning models which enables one to predict the level of sales and level of reviews in relation to multiple internal and external factors (e.g. different shops, product groups, prices, etc.) by combining business knowledge of subject matter experts with historical data. The final results (including interdependencies) are showing avg. precision prediction at the level of 90% making the company excited about the potential of the data-driven approach.
Technology: Python, JupyteR, SkLearn
We have over 10 years of experience in delivery of the top talents to the most demanding enterprise customers based on our own 3 stage technical pre-selection process and strong relationship with top technical universities.
Semantic Search Implementation Expert
Cognitum has provided a talent that helped in the implementation of a semantic search engine which combines documentation data from multiple heterogeneous sources into a single search.
The problem: In large pharmaceutical company an employee who is looking for a solution to his IT related problem, often don’t have an idea where to start to search for a solution. This situation ends-up on submitting a support-ticket to the already overloaded help/service desk.
The search algorithm is using categorisation and text similarity calculations using thesaurus based semantic tagging. Introducing this tool has reduced the overall number of tickets submission by 15%.
The process: Our inhouse team is familiar with semantic search technologies, therefore we have implemented our 3 stage hiring process:
1. technical assessment
2. project fit assessment
3. company-culture assessment
Talent skills: PoolParty Semantic Suite, SPARQL, Apache Stanbol, Apache Solr, SKOS, SPARQL
Outsourcing of C#, C, C++ professionals
We are delivering top professional developers for C #, C ++, C.
Our engineers are taking part in the whole cycle of software development for measuring, alignment, and detection tools.
The problem: expecting top-class specialists with excellent preparation and competent support from outsourcer.
The process: our team consists of specialists in specific technologies, we choose them in an advanced process that we have developed over the years of work.
Our team is familiar with expected technologies (C, C++,C#), therefore we have implemented our 3 stage hiring process:
- technical assessment
- project fit assessment
- company-culture assessment
It’s giving us long-term relationships with our customers.
Talent skills: C#, C, C++,
We are providing comprehensive quality assurance services (manual and automated) in the area of mobile apps, Internet services, enterprise solutions and embedded systems.
Quality assurance for measurement systems
Over 10 years of close collaboration with the Global Leader in the area of Quality Assurance.
The problem: the expectation of custom-developed Quality Assurance solution for desktop and embedded devices
The process: we have prepared and implemented an environment for Automated Tests executed on the desktop and embedded devices. The automation is based on the image recognition algorithm, limiting the effort needed for its maintenance.
Talent skills: C#, Python, SikuliX