Asadbek Abdurashidov
Junior Research Econometrician
I build econometric models for EU transport forecasting at IRU, and AI tools to do it faster.
Geneva, Switzerland · Swiss B permit
abdurashidov.asadbek2201@gmail.com · linkedin.com/in/asadbek-abdurashidov-ba14741ab
About
I research EU transport economics at the International Road Transport Union (IRU) in Geneva, building econometric models that forecast freight demand across the 27 EU member states. My academic work applies causal inference: my bachelor’s thesis used the synthetic control method to measure the GDP impact of Western sanctions on Russia (5.75/6). I pair that quantitative base with hands-on work in AI and multi-agent systems, and I check what the agents produce.
Experience
-
Junior Research Econometrician
International Road Transport Union (IRU) · Geneva, Switzerland
– present
- Build econometric models that forecast freight transport demand across all 27 EU member states.
- Deliver short-term and long-term demand projections used in IRU policy briefs.
- Process and analyse large EU transport datasets in Python and R.
-
Econometric Intern
International Road Transport Union (IRU) · Geneva, Switzerland
–
- Analysed EU transport industry data and developed models projecting short-term and long-term transport demand.
- Ran market analysis to support business expansion.
- Extracted, cleaned and analysed the underlying data.
-
Assistant to WTO Counsellor
Permanent Mission of Uzbekistan to the UN Office · Geneva, Switzerland
–
- Wrote reports for the UN Office and international organisations.
- Supported colleagues in WTO policy work and liaised with embassies.
- Produced daily reports on socio-economic conditions across global regions.
Selected work
The finance, audit and data projects were built by AI agents under my direction, and I checked the results. Each of them states what was checked and what was not.
-
SPIE hypothetical buyout (LBO)
Status: Verified
A hypothetical buyout of SPIE at a 20% takeover premium and a 12× EBITDA exit returns 0.80× money back (−4.3% a year, reference date 31 Dec 2025); without the premium it breaks even.
Checked. Rebuilt independently from its written contract and matched to floating-point precision (largest gap 2e-12); the workbook was recalculated in a separate engine.
Limit. A hypothetical scenario on analyst assumptions: not a transaction and not investment advice.
-
SPIE cash and valuation (DCF)
Status: Verified
In a reconstruction after the fact, SPIE’s FY2025 cash after leases and investment was about EUR 554m, and margins would need to rise from 6.7% to about 8.1% to justify its market value (EUR 8.1bn conditional operating value against a EUR 9.99bn market reference).
Checked. Every input traced to SPIE’s annual reports, with page citations; the valuation was rebuilt independently from the stated assumptions and matched to about 1e-11.
Limit. Uses reports published in 2026. Terminal value is 75% of the total. Not a price target.
-
Independent audit of an AI-built project
Status: Partly verified
I commissioned a second AI to check a first AI’s research line by line: of 91 claims, 68 were supported, 15 partly and 1 contradicted, and the rest were unverifiable, untested or historical.
Checked. Every model was rebuilt independently, the workbooks were recalculated and the sources were re-fetched. The audit’s key finding: the hypothetical buyout’s loss was essentially the 20% premium, which the original headline did not say.
Limit. 129 supporting documents were scanned rather than read line by line, as the report states.
-
EU macro data pilot
Status: Verified
A free data aggregator was missing most recent figures: of 28 comparison points, 6 matched, 18 were missing and 4 differed; the seven official series came from Eurostat, DG ECFIN and the ECB.
Checked. All comparisons were reproduced from the raw downloads, and the official values were re-fetched one day later with no revisions.
Limit. A small sample of series; not a reliability verdict on any provider.
-
Bachelor’s thesis: sanctions on Russia
Synthetic control: measured a 5–6.1% decline in Russia’s GDP per capita from Western sanctions after 2014. Graded 5.75/6.
-
Study tool for the CFA® Program
Status: In progress
Not independently checked
Turns the 10 CFA® Program curriculum volumes into layered study notes with AI.
Education
-
Level I candidate in the CFA® Program (exam February 2027)
-
Bachelor of Arts in Economics
University of St. Gallen (HSG) · St. Gallen, Switzerland
2020 – 2024
- GPA 4.9/6.
- Bachelor’s thesis, 5.75/6: Assessing the Economic Impact of Sanctions on Russia.
-
International Baccalaureate
College Champittet · Pully, Switzerland
2015 – 2020
Grade 34/45.
Skills and languages
- Technical
- Python, R, JavaScript/Node.js, Claude API, LLM orchestration, multi-agent systems, data pipelines
- Finance
- Financial statement analysis, econometric modelling, risk assessment, portfolio management, valuation
- Tools
- Microsoft Office, Git, Claude Code, Obsidian
- Languages
- Uzbek (native), Russian (native), English (C1), French (B1–B2)
How I work with AI
- Direct
- I ran multi-agent research with separate producer and reviewer agents, under written contracts.
- Verify
- I challenged the first portfolio as too shallow, then commissioned an independent audit by a different AI. It found the buyout headline hid its main driver.
- Disclose
- I say where AI agents did the building. Each AI-built project states what was checked and what was not.
Contact
- Location
- Geneva, Switzerland