New research co-authored by Rhema Vaithianathan explores how to best explain machine learning scores.
Watch a recent webinar about how CSDA and its collaborators develop decision aid tools to support front-line child welfare case workers, using data to protect children, support families and improve equity.
A CSDA webinar on Thursday, April 29, 16:00 PM EDT (Friday, April 30, 08:00 AM NZT) will focus on how the centre develops decision aid tools to support front-line Child Welfare case workers, using data to protect children, support families and improve equity
The children of teen mothers in New Zealand have lower baseline school readiness levels than other children and should be prioritised for support, according to new research led by CSDA.
A tool that uses machine learning to help prioritise requests for housing services in Allegheny County, PA (United States), has been credited by frontline staff with helping to make client assessments faster and more efficient.
A talent for connecting research with organisations that can use it, means CSDA’s new business development manager will be a great asset as the centre works to scale out its delivery of predictive analytics tools for social good.
The CSDA team has been contracted to deliver a child welfare decision aid tool for Northampton County, a north-eastern county in Pennsylvania (US), over the course of the next three years.
CDSA Deputy Director Nina Anchugina presented on ‘Covid-19 Contact Tracing Apps: What works?’ at the Chief Data and Analytics Officer (CDAO) NZconference in November.
New UK-based research establishes an association between the daily mood of trainee doctors and their intention to quit.
Human services staff in Allegheny County, Pennsylvania, are using a CSDA tool to match high needs families with intensive support services as part of a proactive child harm prevention program introduced this month.
CSDA has deployed a world-first machine learning tool for a county in the United States, which accurately prioritises requests for housing help.
Nina Anchugina has returned to CSDA as deputy director for the ‘hard problems and human impact’ but also to share her knowledge of private sector best practice with a fast-growing collaborative team.
New research co-authored by Rhema Vaithianathan and Diana Benavides-Prado confirms that children identified as at risk by the Allegheny Family Screening Tool, a predictive risk modelling tool that supports child protection decisions, are also at considerably heightened risk of hospitalisation injury.
New research co-authored by Diana Benavides Prado, a senior research fellow at CSDA, proposes a framework designed to improve the knowledge acquired by machine learning systems that learn sequentially.
Digital contact tracing for Covid-19: new policy primer
Digital contact tracing solutions for COVID-19 must offer exceptional speed and achieve high take-up rates to be useful, according to a working paper released by the Centre for Social Data Analytics (AUT) and the Institute for Social Science Research (UQ).
Rhema Vaithianathan: “NZ is the Wild West of Contact Tracing”
In a recent opinion piece for the NZ Herald Rhema Vaithianathan questioned the requirement for organisations to collect contact tracing data on behalf of the Government and pointed out how this decentralised approach threatens privacy and the trusted use of data.
Allegheny Family Screening Tool in Netflix documentary
A new Netflix documentary series that raises big questions about whether the US child protection system is fit for purpose explores the potential of predictive risk modelling and tells the story of the Allegheny Family Screening Tool, built and implemented by a team led by CSDA Director Rhema Vaithianathan.
“Unassailable research methods” required to influence child maltreatment policy
“To change policy, we need to leverage unassailable research methods,” Professor Jennie Noll told the audience at a recent research seminar hosted by CSDA and AUT’s Policy Observatory.
Douglas County Decision Aide: Methodology Document
The Centre for Social Data Analytics has published a methodology report detailing how it developed and implemented a child welfare predictive risk modelling tool commissioned by the Douglas County Department of Human Services (CO, United States).
CSDA collaboration with Institute for Social Science Research
The Centre for Social Data Analytics has entered into a collaboration with the University of Queensland's Institute for Social Science Research (ISSR) that will see the two research centres work together to establish a social data analytics capability at the University of Queensland.
Insights from the Centre for Social Data Analytics – October 2019
This issue: a new Deputy Director for CSDA; CSDA homelessness work almost ready for implementation; our paper on ethnic disparities in childhood prevalence of maltreatment in the American Journal of Public Health; Rhema delivers the John Western Public Lecture 2019 in Brisbane.
Meet Larissa Lorimer: Executive Coordinator (Research) at ISSR
Larissa has played an integral role in developing CSDA’s Auckland hub since the start in 2016. Now, she is working at the Institute of Social Science Research (ISSR) at the University of Queensland, as an Executive Coordinator of Research, applying those same skills to build the centre’s Australian node.
CSDA researchers share Allegheny Homelessness Tool at D4GX, New York
CSDA Director Professor Rhema Vaithianathan and CSDA research fellow Chamari Kithulgoda attended the Bloomberg Data for Good Exchange (D4GX) in New York in September and presented a poster
Data analytics in the public sector: 2019 John Western Lecture, Brisbane
Professor Rhema Vaithianathan delivered a public lecture - Data analytics in the public sector – the tortoise or the hare? – in Brisbane in September.
Prof Tim Maloney steps down from CSDA
Professor Tim Maloney stepped down as co-director of the Centre for Social Data Analytics in July.
New research: Ethnic disparities in Child Protection NZ
A study co-authored by Professor Rhema Vaithianathan and published in the highly regarded American Journal of Public Health follows the child protection interactions of almost 60,000 children from birth until the age of 18. The study is New Zealand’s first cumulative count of child protection encounters by ethnicity
CSDA work generates strong interest, engagement at US Events
When Director Rhema Vaithianathan presented predictive analytics for child welfare work to four different US audiences, she found strong interest in her work, making useful connections with organisations, funders and policy makers.
Government funding to extend childhood adversities research
A grant from the 2018/2019 round of the Government’s Children and Families Research Fund means CSDA can build on its research into the link between childhood adversities and school readiness.
Allegheny Family Screening Tool evaluation
Researchers from Stanford University have evaluated the Allegheny Family Screening Tool, a child welfare predictive risk modelling tool developed by a team led by Rhema Vaithianathan - and implemented by Allegheny County (US) in 2016.
Family-based factors that protect children against adversities
New research from CSDA has identified family-based factors that are protective for children at risk of experiencing childhood adversities (specific experiences associated with poor outcomes later in life).
Physical spaces and mood – a MyDay pilot study
Researchers at the Centre for Social Data Analytics (AUT) have partnered with an Australasian architectural practice to explore the feasibility of combining a survey on workplace wellbeing with location data, to understand the impact of physical spaces on wellbeing at work.
Meet the team: CSDA Research Fellow Katerina Taškova
CSDA Research fellow and data scientist Katerina Taškova is most interested in doing research that directly affects reality.
At CSDA Katerina has been taking a lead role on child welfare data research projects based in Allegheny County (PA, US) and Chile.
Development economist Sarah Baird visits CSDA
CSDA hosted development economist Sarah Baird from George Washington University (Washington DC) in February. Sarah’s research focuses on the microeconomics of health and education in developing countries, with an emphasis on Sub-Saharan Africa.
Algorithms in the Public Sector Conference
A December conference co-presented by CSDA offered a range of perspectives on the use of algorithms in the public sector, including keynotes from international experts who have commissioned, developed and assessed ethics of public sector algorithms.
Meet the AUT Students working at CSDA
A new appreciation for the role of data analytics in improving people’s lives has been a revelation for one of CSDA’s recent recruits.
“Decision Making: Human vs. Machine” (free public lecture)
This December, Stats NZ and CSDA are presenting a free lecture hosted by international tech ethics expert Lorena Jaume-Palasi. With a background in founding ethics organisations including AlgorithmWatch and the Ethical Tech Society, and consulting to numerous governments and organisations in this space, Jaume-Palasi will present her experiences and recommendations.
CSDA takes a collaborative role in the new US research centre
CSDA Co-director Rhema Vaithianathan will be collaborating with the newly established Centre for Innovation in Child Maltreatment Policy, Research and Training (CICM) at Washington University of St. Louis.
Taking Predictive Analytics with Australian researchers, government
CSDA co-director Professor Rhema Vaithianathan had the opportunity to lead an Australian roundtable about the use of predictive analytics for positive impact in September.
CSDA research in upcoming Child Wellbeing Research Seminar (Wellington)
Matt Walsh, Senior Research Fellow at the Centre for Social Data Analytics (CSDA), will share new research on Adverse Childhood Experiences (ACEs) at a Child Wellbeing Research Seminar hosted by the Ministry of Social Development in Wellington on 11 September.
Seeking feedback on the NZ Guidelines for Trusted Data Use
A year after the launch of the draft NZ Guidelines for Trusted Data Use: ‘A Path to Social License”, the authors have begun to explore how useful the Guidelines are for organisations, and what updates may be needed.
Helping Government to develop Algorithm Guidelines
The Government Chief Data Steward, Liz McPherson, has commissioned Professor Rhema Vaithianathan, co-director of the Centre for Social Data Analytics at AUT, to review international guidelines for the government use of algorithms, and help develop a ‘best practice’ approach for New Zealand.
Meet the Team: CSDA’s Research Fellow Oleksandr Fialko
A background in physics is an essential tool for Oleksandr Fialko who joined CSDA last year as a Research Fellow in Data Science and is working to improve the accuracy of models being used to predict child welfare outcomes.
Researchers ask 2000 trainee doctors what it’s like to walk in their shoes
Researchers working with Health Education England (HEE) in the Wessex region have launched a study that aims to understand how doctors in training in the area experience their working lives.
“Bias Detectives: the researchers striving to make algorithms fair” -CSDA’s work in Nature news.
In late June, an in-depth article and podcast about the CSDA’s work on the Allegheny Family Screening Tool were featured on the Nature news website.
CSDA shares child welfare predictive risk modelling work in Chile
Professor Rhema Vaithianathan, co-director for the Centre of Social Data Analytics, recently gave a keynote address on child welfare predictive risk models at the Adolfo Ibáñez University (UAI) in Santiago, Chile.
International project explores social impact of algorithms
A project led by CSDA’s Co-Director Rhema Vaithianathan, is exploring community perspectives on the use of algorithms in government in New Zealand and the United States.
Surprise findings about interventions helping sick workers
A forthcoming paper in Labour Economics finds at, overall, providing sick workers with more intensive interventions worsened their labour market outcomes.
Social Workers in Schools evaluations: A use case for IDI but we can do more
A study co-authored by CSDA researchers has identified positive effects for some student groups from the government-funded Social Workers in Schools (SWiS) programme. The paper is the first of two studies recently published by the Ministry of Social Development.
CSDA eNews – April 2018
This issue: CSDA risk modelling in the New York Times, funding award to study community perspectives on government use of algorithms, CSDA papers in Children and Youth Services Review, Pediatrics and American Journal of Public Health and meet CSDA Senior Research Fellow Matt Walsh.
Full house for Wellington workshop on child poverty, risk and resilience
There was a great turnout at CSDA’s recent Wellington workshop, attended by individuals from thirteen government agencies and several private sector organisations.
Analysis of screening tool wins best paper award at international fairness conference
A paper that analyses the application of risk modelling to child maltreatment screening decisions will receive a best paper award at the 2018 Conference on Fairness, Accountability, and Transparency (FAT)* in New York in late February.
“Can an Algorithm tell when Kids are in Danger?” – Our research in the NYT
An in-depth feature about a CSDA research project, the Allegheny Family Screening Tool (AFST), ran in the New York Times Magazine in January.