Ainura Tursunalieva

Ainura Tursunalieva

Auto-generated profile, based on publicly available information

Ainura Tursunalieva

Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, Australia

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
5 January 2024 in Applied Sciences
Verified
Journal Article
Open access
ATAinura Tursunalieva
Ainura Tursunalieva
DADavid Alexander
David Alexander
RDRob Dunne
Rob Dunne
JLJiaming Li
Jiaming Li
LRLuis Riera
Luis Riera
Yanchang ZhaoYanchang Zhao
Yanchang Zhao
Transparency in AI models is essential for promoting human–AI collaboration and ensuring regulatory compliance. However, interpreting these models is a complex process influenced by various methods and datasets. This study presents a comprehensive overview of foundational interpretation techniques, meticulously referencing the original authors and emphasizing their pivotal contributions. Recognizing the seminal work of these pioneers is imperative for contextualizing the evolutionary trajectory of interpretation in the field of AI. Furthermore, this research offers a retrospective analysis of interpretation techniques, critically evaluating their inherent strengths and limitations. We categorize these techniques into model-based, representation-based, post hoc, and hybrid methods, delving into their diverse applications. Furthermore, we analyze publication trends over time to see how the adoption of advanced computational methods within various categories of interpretation techniques has shaped the development of AI interpretability over time. This analysis highlights a notable preference shift towards data-driven approaches in the field. Moreover, we consider crucial factors such as the suitability of these techniques for generating local or global insights and their compatibility with different data types, including images, text, and tabular data. This structured categorization serves as a guide for practitioners navigating the landscape of interpretation techniques in AI. In summary, this review not only synthesizes various interpretation techniques but also acknowledges the contributions of their original authors. By emphasizing the origins of these techniques, we aim to enhance AI model explainability and underscore the importance of recognizing biases, uncertainties, and limitations inherent in the methods and datasets. This approach promotes the ethical and practical use of interpretation insights, empowering AI practitioners, researchers, and professionals to make informed decisions when selecting techniques for responsible AI implementation in real-world scenarios.

1 July 2016 in Insurance: Mathematics and Economics
Verified
Journal Article
Closed access
ATAinura Tursunalieva
Ainura Tursunalieva
PSParam Silvapulle
Param Silvapulle

1 January 2019
Verified
Book Chapter
Closed access
PDF file
ATAinura Tursunalieva
Ainura Tursunalieva
IHIrene Lena Hudson
Irene Lena Hudson
JCJ. Geoffrey Chase
J. Geoffrey Chase

11 April 2019 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
RDRatbek Dzhumashev
Ratbek Dzhumashev
ATAinura Tursunalieva
Ainura Tursunalieva
This paper presents a new method for synthesizing instrumental variables using only the dependent and endogenous explanatory variables of the regression model. We show that a valid instruments can be spanned using the dependent and endogenous variables. Then based on this rationale, we construct an estimator that uses moment conditions stemming from the validity of such synthetic instruments. We demonstrate the consistency of the newly-developed estimator using synthetic variables. A computational algorithm is developed using the moments conditions stemming from the consistency of the estimator. One can use this synthetic instrumental variables method as an alternative to traditional external instruments methods.

10 July 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
ATAinura Tursunalieva
Ainura Tursunalieva
RDRatbek Dzhumashev
Ratbek Dzhumashev
We document a structural change in the determinants of dwelling prices and rents across Australia's five largest capital-city markets and characterise how a common credit impulse propagates through each. Using quarterly data from 2006 to 2025, we estimate two reduced-form equations exploiting within-city variation over time. Rents are consistently explained by market fundamentals: a migration-to-completions measure of housing-market tightness, wage growth, and employment, with the employment channel strengthening over time. Prices differ. Investor mortgage demand co-moves much more strongly with prices than with rents, and this asymmetry sharpens after 2017. Because credit and prices are jointly determined within the quarter, we bracket rather than pin down a single elasticity for their relationship. The contemporaneous association is large and remains economically meaningful even when credit is treated as predetermined. Panel local projections trace the transmission dynamics: investor-credit innovations are capitalised into prices immediately but reach rents only with a delay. In the preferred specification, rents respond little during the first year, then rise gradually, with prices and rents converging over a three-year horizon. The decoupling thus reflects differences in transmission speed rather than permanent insulation of rents from financial conditions. The strengthening of the price-investor-credit channel is broad-based in the pooled panel and is not concentrated in Sydney. We interpret the breakdown in the price-rent relationship as evidence that the two markets are increasingly governed by different forces: rents by local fundamentals and prices by investor finance. Our contribution is to document this separation rather than to identify the effects of any particular policy.

20 March 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
ABAlexandra Bratanova
Alexandra Bratanova
HCHaohui Chen
Haohui Chen
HPHien Pham
Hien Pham
ATAinura Tursunalieva
Ainura Tursunalieva
SDSimon Dunstall
Simon Dunstall
GBGuy Bruce Barnett
Guy Bruce Barnett
Extreme heat is Australia’s deadliest natural hazard, accounting for nearly 80% of extreme weather-related hospitalisations between 2012–13 and 2021–22 and contributing to 293 deaths. These risks are expected to intensify with climate change as heatwaves become longer and more severe. When heat events coincide with loss of electricity supply (LOS), health impacts can escalate sharply because common cooling strategies are disabled. This study assesses population vulnerability to concurrent extreme heat and LOS across Australia. Unlike most analyses that consider heat in isolation, it examines the interaction of heat and power disruptions.The assessment is conducted using the Exposure–Sensitivity–Adaptive Capacity framework at the Statistical Area Level 1. Eighteen indicators captured exposure to heat, socio-demographic factors associated with sensitivity, and elements of adaptive capacity. The study identifies three clusters among the 10% most vulnerable regions under combined conditions: (1) remote regions with high heat exposure and limited service accessibility; (2) communities with lower education and constrained adaptive resources; and (3) suburban populations with high proportions of older residents and limited English proficiency. These distinct profiles highlight the limitations of uniform interventions.The resulting cluster typology offers an evidence base for targeted adaptation—from strengthening energy system resilience to operational measures such as prioritised power restoration, wellness checks, and tailored risk communication. The analysis also identifies data gaps that, if addressed, would improve future risk assessments. Overall, the study advances understanding of compound climate–health risks and provides a scalable framework for identifying populations most vulnerable to associated stresses.