Elnorakhon Muminova

Elnorakhon Muminova


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 October 2026 in Sustainability
Verified
Journal Article
Open access
PDF file
SARDORBEK KODIROVSARDORBEK KODIROV
SARDORBEK KODIROV
EMElnorakhon Muminova
Elnorakhon Muminova
GXGo’Zal Xankeldiyeva
Go’Zal Xankeldiyeva
SDSherzod Dehkanov
Sherzod Dehkanov
DKDilnoza Khudoyberganova
Dilnoza Khudoyberganova
Studies of Chinese regions, mostly using composite indices and estimated or allocated emissions, report that digitalisation reduces carbon emissions. This study re-examines the claim for one component of digitalisation, network quality, using directly measured quantities: tropospheric nitrogen dioxide (NO2) columns from the Tropospheric Monitoring Instrument (TROPOMI) and crowdsourced Ookla speed and latency measurements for 161 districts of Uzbekistan in 2019–2025 and 42 regions of Central Asia. Fixed-effects panel regressions with a correction for the 2021 TROPOMI processor change and population controls give an elasticity of NO2 with respect to mobile download speed of 0.001 (95% confidence interval −0.013 to 0.015). Given the 7.4-fold rise in the average district’s speed, this interval bounds the associated change in NO2 between −2.6% and +3.0%. The estimate remains small and insignificant with meteorological controls, in a consistently reprocessed TROPOMI record, at quarterly resolution and with speed from a fixed set of map tiles. An equivalence test rejects elasticities of 0.013 or more in absolute value. None of the three heterogeneity hypotheses from an unregistered analysis plan survives a Holm correction. District-level emissions from the Emissions Database for Global Atmospheric Research (EDGAR) for road transport and buildings largely reproduce national changes. Within districts, faster mobile networks were not associated with a measurable change in NO2.

20 September 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
EMElnorakhon Muminova
Elnorakhon Muminova
JYJamshid Yuldashev
Jamshid Yuldashev
NNNilufar Nabiyeva
Nilufar Nabiyeva
AKAbdumalik Kadirov
Abdumalik Kadirov
MMMashxura Mamayusupova
Mashxura Mamayusupova
SMSarvinoz Mamatojieva
Sarvinoz Mamatojieva
Cross-country measures of Islamic finance development are weighted toward realised market outcomes and therefore assign near-identical scores to jurisdictions that differ substantially in institutional preparation but have yet to accumulate Shariah-compliant assets. Uzbekistan is an instance of that configuration and, because the sector is new, one in which the underlying structure can be observed directly. This study examines the first eighteen months of Shariah-compliant finance in Uzbekistan using supervisory returns covering the complete population of licensed providers, together with the banking law that entered into force in June 2026. Financing grew almost eightfold year on year, yet the market is extraordinarily concentrated: the Herfindahl-Hirschman index reaches 6,019, an effective supplier count of 1.66, and 94.0 percent of activity is confined to the capital. Concentration was stable between the two observed quarters while the identity of the dominant providers changed entirely, and the Gini coefficient rose from 0.47 to 0.59. Product structure diversified sharply, the effective number of instruments rising from 1.00 to 1.91 within twelve months, with the profit-and-loss sharing instrument concentrated in the household segment. The evidence indicates that legal permission and market capability are separated by a measurable interval, and that institutional readiness advances ahead of market breadth.

16 October 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
SARDORBEK KODIROVSARDORBEK KODIROV
SARDORBEK KODIROV
EMElnorakhon Muminova
Elnorakhon Muminova
GXGo'Zal Xankeldiyeva
Go'Zal Xankeldiyeva
SDSherzod Dehkanov
Sherzod Dehkanov
DKDilnoza Khudoyberganova
Dilnoza Khudoyberganova
A large literature, mostly on Chinese provinces and cities, reports that digitalisation reduces carbon emissions. Most of this evidence relies on composite digital-economy indices and on emission figures that are estimated or spatially allocated rather than observed. This study tests the claim with directly measured quantities: tropospheric nitrogen dioxide (NO2) columns from the TROPOMI satellite instrument and crowdsourced Ookla measurements of network speed and latency, for 161 districts of Uzbekistan in 2019–2025 and 42 regions of Central Asia. District-level changes in gridded EDGAR CO2 emissions for road transport and buildings closely reproduce national changes, which makes such inventories unsuitable as sub-national outcomes. Panel regressions with district and year fixed effects, a correction for the July 2021 change in the TROPOMI processor, and population controls give an elasticity of NO2 with respect to mobile download speed of 0.001 (95% confidence interval −0.013 to 0.015). The average district's speed rose about 7.4-fold over the period, so the associated change in NO2 is bounded between −2.6% and +3.0%. No alternative specification or regional estimate is statistically significant, and none of three pre-specified heterogeneity hypotheses survives a Holm correction. Within districts, faster mobile networks were not associated with a measurable change in NO2.

5 November 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
SARDORBEK KODIROVSARDORBEK KODIROV
SARDORBEK KODIROV
Azizjon MeliboevAzizjon Meliboev
Azizjon Meliboev
EMElnorakhon Muminova
Elnorakhon Muminova
IKIlyos Khasanov
Ilyos Khasanov
STShohruhjon Temirov
Shohruhjon Temirov
Banks and financial technology providers often train churn models on several historical snapshots of their customer base, a practice known as multi-slice training. Evidence for its benefits rests on few datasets, and widely used random row-wise validation can place copies of one customer record in training and test data. We test the practice under an analysis plan written before any model was trained on the bank data, using public transaction histories of 98,721 corporate clients of Sber (2021–2022) and 50,000 retail clients of T-Bank (2019–2020), with churn defined as three months without transactions. Models trained on the latest slice are compared with models trained on all slices, using out-of-time and customer-disjoint test sets, DeLong tests and the expected maximum profit criterion. Multi-slice training changed the area under the receiver operating characteristic curve by +0.0005 for corporate and +0.0011 for retail clients, within the pre-specified equivalence margin of ±0.005, and raised expected campaign profit by 1.2% for corporate clients only. At equal sample size, older slices performed worse than the latest slice. Random row-wise validation inflated performance markedly only when slices duplicated customer snapshots. In Uzbekistan, Central Bank and Global Findex data show registrations consistent with multi-banking and falling concentration.