The web page uses cookies, which enable and facilitate your use of its resources. On our website we use cookies which are stored on the hard drive of your device in order to customize our web page to individual user preferences and to carry information across pages of the website without having to re-enter such information (eg. log on, where required), as well as for statistical purposes. Cookies can be removed or declined by changing your web browser settings. By using the web page you consent the use of cookies according to your browser settings


Banking and Financial

BI and Data warehousing

ASEBA Tezauri Scoring and Rating Solution


ASEBA Tezauri Scoring & Rating Solution

Need to evaluate your client’s credit rating? Try ASEBA Tezauri Scoring & Rating Solution to take your business to the next level.

ASEBA Tezauri Scoring & Rating Solution® has everything you need to minimize a risk of your business and increase your profit. Offered as standalone software solution, seamlessly integrated with your corporate environment with zero maintenance and ultra-low requirements.

Solution is aimed at financial institutions and other vertical markets where there is need for high performance calculation/decision support. Typical application is assessment of credit risk, but it can be applied in any domain of decision making where necessary. Sophisticated calculation engine is based on industry standard decision tree algorithm.


Predicting future outcomes and identifying factors that can produce a desired effect are often the main goals of data analysis and data mining. Decision trees are one of the most popular methods of predictive modeling for data mining purposes because they provide interpretable rules and logic statements that enable more intelligent decision making.

A decision tree partitions data into smaller segments called terminal nodes or leaves that are homogeneous with respect to a target variable. Partitions are defined in terms of other variables called input variables, thereby defining a predictive relationship between the inputs and the target. This partitioning continues until the subsets cannot be partitioned any further using user-defined stopping criteria. By creating homogeneous groups, analysts can predict with greater certainty how individuals in each group will behave. For example, in database marketing, decision trees can be used to segment groups of customers and develop customer profiles to help marketers produce targeted promotions that achieve higher response rates.

Decision trees are just one of the advanced analysis models included ASEBA Tezauri - Scoring and Rating Solution® and they are often used during preliminary predictive modeling. For instance, you may want use decision trees for variable selection and then mine the reduced dimension data set with a more resource intensive neural network. It is also common to use decision trees to segment the data and then use another predictive modeling method to predict the response in each segment.

ASEBA Tezauri - Scoring and Rating Solution® offers numerous features for comparing the results of different modeling techniques in business terms as well as through statistical diagnostics. This provides the unique ability to gauge model effectiveness in terms of overall profitability, enabling the quantitative analyst to easily share and discuss essential results with business users.

Original on-premise solution was developed during 2004 with primary goal to suit need of on-line credit scoring calculation. Scenario covered on-line access to ODS data. Also covered were various integration scenarios for batch and single entry processing.

In 2008 second generation of solution was developed and released to the market. Scenario of batch processing was in focus of this release. Needs for high performance calculation on large volumes of data has driven development of new processing/calculation engine, optimized for batch performance. Engine delivered expected improvement. In case study we did for large customer we measured improvement of factor 37. For batch size of 500.000 customers scored, time was reduced from 12 hours to less than 20 minutes (compared to first generation).

Typical usage scenario consists of use of scoring models for following purposes:

-          Internal rating calculation, depending on customer size 3 to 10+ models are deployed covering different parts of portfolio. Models are based on internal policies consisting of various quantitative and qualitative indicators, linked with custom logic to calculate rating of client.

-          External rating calculation, scoring models used for calculation of client rating based on legislative regulations. Output from scoring models are usually utilized in other processes, some of which are offered through other modules of Asseco SEE ASEBA portfolio

-          ATP calculation, gathering of data from external credit organizations, such as credit bureau, register of companies, treasury, etc, and appliance of specific calculations in process of loan improvement.

Although separate, those processes are often combined inside back office to create rich picture, and help evaluate risks. 

Our solution addresses problem of accessing risk in real time:

  • Track risk in a near-real time during:
    • Subscriber/customer acquisition
    • ongoing usage
    • collections and recovery
  • TSRS provides the helps in understanding subscriber/customer risk profile
  • Quickly and seamlessly, accommodate new service information to provide an accurate picture of the exposure at any point in time.
  • Allowing to easily and quickly defining various risk indicators and controls enables to adapt to local cultural and regulatory requirements.
  • Enables to stay agile in changing socio-economic conditions that affect the overall level of risk in a region.
  • Operations process analysis and design around the customer life cycle, including credit, usage, collections, write-offs, and recoveries
  • Portfolio management including account segmentation, experimental design, and P&L optimization
  • Organization development including organization design, skill set requirements, and position descriptions
  • Decision analytics providing predictive modeling development and implementation
  • Systems development and integration covering functional/technical requirements, interface development, testing, and training
  • Understand your customer portfolio across the entire credit lifecycle - develop policies and strategies from account activation to collection and recovery.
  • Use quantitative analytics to understand and manage trends within your portfolio - capture and retain data for segmentation, analysis, and behavioral scoring.
  • Create environment of continuous learning through "test-and-learn" discipline use champion/challenger, controlled experimentation
  • Align business processes, technology, and organization structure - optimize cost efficiencies and effectiveness
  • Reduce net bad debt expenses
  • Lower costs from credit and collections operations
  • Improve cash flow
  • Retain customers
  • Increase top-line revenues

Concepts dictionary

  • Schema (model) for credit scoring is criteria (questions) group which is exerted for specified scenario (or defined client type and similar…) with proper ponders and scoring way.
  • Criteria can have sub criteria. In that case for every criteria relative ponder has to be entered (define influence of sub criteria on main criteria)
  • Number of points is assigned to every possible interval of answer values
  • Answer values can be entered manual, or automatically acquired from database
  • Question which are not leaves getting answers applying by one of standard algorithm (MAX, MIN, AVG, SUM, TREND...), or custom algorithm defined in stored procedure, on answers of child question


  • SQL Server 2005-2012 (Express or better)
  • Internet Information Services 6.0/7.5/8.0
  • Active Directory Federated Services 2.0
  • Windows Server 2003 or better

Solution is coded in C#, and targets .net framework 3.5SP1


ASEBA Tezauri Scoring and Rating ® supports the following main functionalities:

  • Supports single and batch processing of credit applications from various data sources
  • Definition of scoring models
  • Credit application analysis
  • Definition of business rules
  • Group and individual scoring based on decision trees
  • Optimized for massive processing
  • Keeps scoring history for advanced analysis
  • Testing and validation of scoring models
  • Built on latest server technologies 
  • Multi-core CPU optimized 


  • Komercijalna  Banka A.D. Beograd,  Serbia
  • Komercijalna Banka A.D. Budva, Montenegro
  • Komercijalna Banka A.D.  Skoplje, FYR Macedonia
  • NLB Tutunska Banka A.D. Skoplje, FYR Macedonia
  • Izvozna  i  Kreditna Banka A.D. Skoplje, FYR Macedonia
  • Stater Banka, Kumanovo, FYR Macedonia
  • Stopanska Banka A.D. Bitolj, FYR Macedonia     
  • Ohridska Banka A.D. Ohrid, FYR Macedonia
  • Banka Intesa  A.D. Beograd,  Serbia
  • BBAC  Beirut, Lebanon
  • Findomestic Banka A.D.  Beograd, Serbia
  • PBB A.D. Beograd, Serbia
  • Credit Agricole Banka  A.D. Serbia
  • Alpha Banka A.D. Beograd, Serbia
  • Allianz Bank, Bulgaria
  • IK banka Zenica, Bosna & Hercegovina.
  • Mikrokreditno druątvo "Sinergija plus" Banja Luka, Republic of Srpska
  • Komercijalna Banka A.D. Banljaluka, BOSNIA & HERCEGOVINA 
  • Podravska Banka D.D. Zagreb, Croatia

What's more

The group Asseco SEE is the largest operator in South-Eastern Europe in terms of revenue derived from sales of its software and services. We offer competence, experience, knowledge and dedicated solutions.

We came into being as a result of the integration of competence, experience, knowledge, solutions and customer base of the nine major IT companies companies, operating in the region of Southeastern Europe.

Banking software product portfolio of Asseco South Eastern Europe covers following product lines: Core Banking Systems, Payment Systems, Channel Systems, Business Intelligence Systems.