Interpretable AI & Women in Data Science

The ORSNZ is sponsoring an event next Monday (10 February 2020) with two international experts in the field of data science and machine learning. This is being hosted at the University of Auckland, as a NZ Data Science + Analytics Forum event.

The event will be held from 3:45pm-6:00pm in the Neon Lecture Theatre in Engineering (401.439) at 20 Symonds Street. There will be pizza and drinks provided after the presentations.

Parking is available in the Owen G Glenn Building (OGGB) carpark accessed via Grafton Road, opposite Stanley Street.

The event is free of charge and kindly sponsored by the University of Auckland and the Operations Research Society of New Zealand.


Professor Margot Gerritsen from Stanford University is the co-director and co-founder of the global Women in Data Science (WIDS) phenomenum. Started as a conference at Stanford in November 2015, WiDS now includes a global conference with approximately 150+ regional events worldwide and a datathon, that encourages participants to hone their skills using a social impact challenge. Professor Gerritsen is also the host of the very popular WIDS podcasts featuring leaders in data science talking about their work, their journeys, and lessons learned.

Professor Dimitris Bertsimas has consulted widely in a variety of industries and has co-founded several very successful Analytics/AI startups. These include Dynamic Ideas (subsequently sold to American Express) which developed machine learning methods for asset management, D2 Hawkeye, a data mining health care company specialising in machine learning, and most recently P2 Analytics LLC, a consulting company and Interpretable AI, a machine learning company. Professor Bertsimas’ talk will focus on this latter work where he is building AI solutions that are human explainable. The benefits of using models, such as decision trees, that humans can interpret are well recognised. However, these models have often given poor performance when compared with black-box approaches. The dominant approaches for generating interpretable models were developed in the 80s, when computing power was limited. Bertsimas’ work is leveraging advances in modern optimization to revisit these approaches, delivering models that are both high performing and interpretable.

Come along and hear from these two international leaders in data science and artificial intelligence.


Professor Margot Gerritsen, Stanford University, USA

Professor Gerritsen was born and raised in the Netherlands. After receiving her MS degree in Applied Mathematics at the University of Delft, she moved to the U.S. in search of hillier and sunnier places. In 1996 she received her Ph.D. in Scientific Computing and Computational Mathematics at Stanford University. Before returning to Stanford in 2001, she spent nearly five years in Auckland, New Zealand as a faculty member in the Department of Engineering Science.

Professor Gerritsen is a professor in the Department of Energy Resources Engineering at Stanford, interested in computer simulation and mathematical analysis of engineering and natural processes. From 2010 to 2018, she directed the Institute for Computational and Mathematical Engineering ( Since 2015, she has been the Senior Associate Dean for Educational Affairs in the School of Earth, Energy and Environmental Sciences, as well as the co-director of Women in Data Science (WiDS, and the host of the WiDS podcasts.

Professor Dimitris Bertsimas, MIT, USA

Professor Dimitris Bertsimas is currently the Boeing Professor of Operations Research, the Associate Dean of Business Analytics at the Sloan School of Management, MIT. He received his SM and PhD in Applied Mathematics and Operations Research from MIT in 1987 and 1988 respectively. He has been with the MIT faculty since 1988. His research interests include optimization, machine learning and applied probability and their applications in health care, finance, operations management and transportation. He has co-authored more than 200 scientific papers and five graduate level textbooks. He is the editor in Chief of INFORMS Journal of Optimization and former department editor in Optimization for Management Science and in Financial Engineering in Operations Research. He has supervised 72 doctoral students and he is currently supervising 25 others.

Professor Bertsimas is a member of the National Academy of Engineering since 2005, an INFORMS fellow, and he has received numerous research and teaching awards including the John von Neumann theory prize for fundamental, sustained contributions to the theory of operations research and the management sciences and the president’s award of INFORMS recognizing important contributions to the welfare of society, both in 2019, the Morse prize (2013), the Pierskalla award for best paper in health care (2013), the best paper award in Transportation (2013), the Farkas prize (2008), the Erlang prize (1996), the SIAM prize in optimization (1996), the Bodossaki prize (1998) and the Presidential Young Investigator award (1991-1996).

Professor Bertsimas has consulted widely in a variety of industries and has cofounded several very successful companies. In 1999, he co-founded Dynamic Ideas, LLC, which developed machine learning methods for asset management. In 2002, the assets of Dynamic Ideas were sold to American Express. From 2002-2010, he was the head of the quantitative asset management group of Ameriprise Financial, responsible for $12 billion of assets. In 2001, Bertsimas cofounded D2 Hawkeye, a data mining health care company and responsible for its machine learning capabilities. The company was sold to Verisk Health in 2009. In 2011 he cofounded Benefits Science Technologies LLC, a company that designs health care benefits, Savvi Financial LLC, a financial advice company and Alpha Dynamics LLC, an asset management company. In 2015 he cofounded P2 Analytics LLC, a consulting company and in 2018 Interpretable AI, a machine learning company.

Represent ORSNZ at IFORS 2020

Dear ORSNZ members,

There is an opportunity to represent ORSNZ at the upcoming IFORS (given that the Coronavirus situation has been resolved). Our IFORS representative, Andy Philpott, is not going to IFORS this year so if you are planning on going and would like to represent ORSNZ please let me know (president[AT] Below is a letter to Andy that outlines some opportunities for ORSNZ’s rep at IFORS 2020.

Kind regards,
Mike (ORSNZ President)


IFORS 2020 is coming up and I do hope to see you there. As you know, it is during our Triennial Conferences that we get to meet during the Board of Representatives meeting where the Administrative Committee reports on its activities.

We would like to hear from you, our members, and for this, we have organized a session called the Lightning Talks and the Roundtable Discussion which I describe below.   

Lightning Talks- Perspectives on the Local State of OR and the Role of National Societies 

The lightning talks are intended to be a way of opening up windows into different aspects of OR practice across various national settings and how each national society performs its role of promoting the discipline. Representing a country, each speaker will deal with the national state of OR study and practice, which forms the backdrop in which the national OR society operates.  For one hour, five speakers will each be asked to do a 10-minute presentation. The idea is for the audience to get an overview of the state of OR study and practice in the locality. For the second half, each speaker will touch on the successes and challenges faced by the society and how these are achieved and addressed, respectively. These talks are meant to drum up interest of the audience, stimulate discussions, and provide food for thought for the succeeding session on how OR national societies tackle the successes and challenges that face them in the short term and on the long term as they strive to fulfill their objectives.

Roundtable Discussion: Learning from Successes and Challenges of National OR Societies 

This 1-1/2 hour session will involve dividing participants into small groups of not less than 5 per group. During the group discussion, each participant will speak for his or her society, guided by a questionnaire. Each group will have a facilitator, recorder and reporter. At the end of the session, reports from each group will be shared with the audience.

The group will tackle these questions:

  1. How is OR practice and education in your country?
  2. How has this affected your national OR society? 
  3. What did your national society do well? In which aspects could it do better?
  4. Are there other experiences shared by others that you could try with your national society?
  5. What do you think are your society’s key success factors?
  6. What could IFORS and/or its national societies do to help countries who are struggling to drive OR forward?

At the end of 50 minutes, each table will have a reporter who will tell the others the summary of what their group has discussed.  A secretary will record all key points and this could be included in a report or article for IFORS.  ​

I am inviting you to participate in this session. While I realize that you may not be able to come, I do hope that you’ll exert every effort to see that your society is represented. You may have some associates who are presenting papers and they could still participate in the session as this is exempted from the one-author-one-abstract rule.

The session is still being scheduled. Please coordinate with former IFORS President Elise del Rosario (REDACTED) who is putting together this session.

Grazia Speranza
President, IFORS

ORSNZ Conference Planning 2020

We are starting to think about the location and timing of this year’s conference.

In terms of the 2019’s conference: we found that that having sessions based around research topics (rather than YPP / non-YPP) went well; however, in future it would be great to be able to conclude the conference with an analytics forum (or similar) event / drinks, rather than have that on the same night as the dinner.

We think that last year’s conference went well by ourselves, but for organisational reasons, would prefer to align with other conferences, where appropriate.

We are conducting a survey to see what other societies are hosting conferences in late November / early December 2020, so we can either: join them, align with them, or avoid a clash.

For example, we are aware that the 2020 NZMS Colloquium is running from 1-3 December 2020 at AUT.

Please submit any conferences that you know of, using the link below:
Go to Survey

This survey will close on Friday 31 January; and will be followed up with another survey to determine a preferred location for the conference.

ORSNZ Annual General Meeting 2019

At the upcoming ORSNZ conference, we will have our Annual General Meeting on Wednesday, December 4 (exact time has yet to be determined).

The agenda for the meeting is:

  1. Apologies (to [email protected]);
  2. Minutes of the previous AGM;
  3. Matters arising from the minutes;
  4. President’s report;
  5. Honorary Treasurer’s report and financial statements;
  6. Future Conferences;
  7. Election of officers and auditor;
  8. Other business.

Please send through additional agenda items to [email protected] by 5pm Friday 22 November.

If you cannot attend the meeting, you can assign a proxy to vote on your behalf using the 2nd page of this form. (So long as the form is emailed to [email protected] by the morning of Wednesday December 4, that is fine.)

Extended Deadline for Abstracts and Early-bird Registration for upcoming ORSNZ conference

We have just extended the deadline for abstract submissions and early-bird registration by 1 week, these are now due by Friday November 8.

We have made a minor change to the programme, with Prof. Vicky Mabin’s plenary address entitled: Use of Reframing in Evidence-Based Modelling to Support Policy Decisions now scheduled for Tuesday morning (December 3).

We are also fortunate to now have a keynote address by Dr James Tipping from the Electricity Authority, which has been scheduled for Wednesday (December 4), to kick-off the sessions on energy and emissions. These sessions will conclude with a panel discussion chaired by Adjunct Prof. Grant Read.

More details about the programme are available here.

CHANGE OF DATE: ORSNZ Conference 2019

Due to a scheduling conflict with another conference, the ORSNZ conference has been shifted by one day. We have already individually contacted everyone who has already registered.

The conference will therefore be held from Tuesday, December 3 to Wednesday, December 4; below is an updated schedule, which can also be found on the conference website, here.

Tuesday, December 3

The first day of the conference (Tuesday) will have a Healthcare Analytics focus, with at least session on Healthcare, a plenary by Prof. Margaret Brandeau (Stanford University), and an Analytics Forum event, focussed on Healthcare.

The conference dinner will be held from 6:30 on Tuesday evening.

Wednesday, December 4

The second day of the conference will have a plenary by Prof. Vicky Mabin, (Victoria University of Wellington), and at least one session on Energy and Emissions as well as a panel discussion on emissions and carbon-neutral policies.

YPP and JAG prizes will be awarded at the conclusion to the conference.

Monday, December 2

Sponsored by Healthier Lives – He Oranga Hauora

Prior to the conference, on Monday December 2, Prof. Margaret Brandeau (Stanford University) is running a day-long workshop on Health Systems Modelling. The workshop runs from 9am-4:30pm and workshop details can be found here.