What does SEPPAS stand for and what is our business case about?

SEPPAS stands for Slovenian Electronic Public Procurement Analysis Services and is centred around Slovenian public procurement data. The main focus is to detect corruption, searching for anomalies in the data to detect patterns that could indicate or fraud or otherwise suspicious activity.

Brief overview of the Slovenian economic environment

Slovenia has been a member of the EU since 2007 and has recorded very encouraging economic indicators in previous years. Annual GDP growth is hovering around 3,5-5% and was nominally around 48 billion EUR in 2019. The below figure indicates the volume of public procurement in the country since 2011.

Image 1: Percentage of public procurement expenditure in Slovenia as a fraction of GDP.

What is the general idea and approach to our business case?

Slovenia has a useful collection of historic public procurement data that is being analysed within the scope of the TBFY project. Data is systematic and structured, so it is suitable for analysis and experimenting with new approaches to detect anomalies.

Slovenian Public Procurement is worth over 4.1bn EUR in terms of public procurement contracts annually and that is a significant part of public spending in Slovenia. Public procurement must be as transparent as possible and there are a number of rules and regulations in place to ensure all the proceedings meet the high standards of the Slovenian government.  

One way to ensure standards are followed is to search for anomalies. Different approaches can be utilised in anomaly detection. One approach would be to feed all the data into a data analysis engine and run anomalies detection algorithms. This means that a very experienced public procurement professional will have to interpret the results that the algorithms produce to determine their usefulness. The second approach would be to set predetermined markers and then check for these results from the algorithmic output. What we propose is a hybrid of these two approaches where we set several indicators that are checked but we still allow the algorithm to run the data and display »red flags«. A skilled public procurement professional will still be needed to assess the importance of the outcomes and present them to the interested public.

What do we hope to gain from anomaly detection?

We hope our findings will help us improve the public procurement process in Slovenia and make it more transparent. The more transparent the process is, the more bidders we hope to attract so the more economically sound the whole procurement process becomes.

A recent World Bank study has found that an increase in the number of bidders yields significant savings in public procurement (in the range of 20%). With public procurement in Slovenia being worth more than 4.6bn EUR in 2018 this could mean savings in excess of 900m EUR.

We also envision linking our public procurement data with other public databases, thus improving transparency even further. Moreover, there are other tools being developed to further facilitate public procurement. One added benefit would be a tool that lets public procurement specialists know what to expect when preparing a bid. An example of such welcome information would be:

  • the number of bids to expect (that would influence the choice of public procurement procedures to choose),
  • an average distribution of bids,
  • average decision time.

One tool being developed in this context is a decision tree which shows graphically the importance of parameters when conducting a public procurement procedure. It shows the factors which need to be implemented for maximizing the probability of success, defined as a procedure receiving a valid bid.

Image 2: Example of a decision tree.

Of course, we always strive to acquire more than one valid bid as this shows the process is economically sound and that the procurement market is competing for business. To achieve this, our business case is also designed to detect collusion and other unfair practices. Agents might be unfairly coordinating their activities to influence the market which negates the basic principles of public procurement. These types of activities must be detected as soon as possible, and offenders prosecuted to the full extent of the law, barring their further cooperation in public procurement procedures.

 

Example: number of employees of a bidding party

Figure 3: Tender value vs. Number of employees ratio.

One example of an analysis we consider in Figure 3 is the number of employees of a bidding organization and the value of a specific tender. The rationale here that it is unlikely to see high value tenders being won by a bidder with an abnormally low number of employees, which could indicate fraud. It does not automatically mean that there are unfair business practices behind this, however it does raise suspicion and warrants further investigation. Even more so if additional warning signs are also present, such as high occurrence of the same bidder winning tenders or if the same economic entity (or the owner) has faced criminal charges or sentences in other countries. Assessing this risk would obviously fall on an experienced public procurement specialist and involve specialized prosecution officers who are experts in economic criminal activities.

 

Our tools also help us focus on social considerations in the so-called Most Economically Advantageous Tender (MEAT) award criteria to foster sustainable public procurement. MEAT refers to awarding contracts on the basis of criteria other than price, such as social and environmental considerations and quality criteria. Social public procurement aims to increase the level of social criteria used in public procurement procedures. It may take into account a number of factors, such as:

  • employment possibilities;
  • adherence to labour standards;
  • social inclusion of persons with disabilities and the elderly
  • equal opportunities for men and women;
  • promotion of permanent employment;
  • social responsibility; and
  • average salary of personnel.

Social criteria considerations in public procurement are an important aspect of public procurement and are specially regulated in Slovenian public procurement legislation. Beyond our work in anomaly detection, we are planning to use the tools developed in the TBFY project to monitor further the implementation of social criteria in public procurement.

 

Mitja Medvešček is Secretary of the Public Procurement Directorate at the Ministry of Public Administration in Slovenia.