EuSpRIG Annual Conference

EuSpRIG: The World’s Leading Spreadsheet Risk Management Conference

The European Spreadsheet Risk Interest Group Conferences are back!

Thursday, July 6th 2023 – The Foundling Museum, London.

Click here to register

Programme (download PDF)

Bringing generative AI to the Excel grid: from research to practice (Keynote)
Andrew D. Gordon and Jack Williams,
Calc Intelligence Microsoft Research
Team link: https://aka.ms/CalcIntel
Learn how to transform your textual data within the Excel grid using the new LABS.GENERATIVEAI() function. It empowers Excel users with OpenAI’s pre-trained language models. It’s part of the new add-in Excel Labs, a Microsoft Garage project that also delivers new formula editing and reuse features, including easy editing of LAMBDAs. We’ll showcase the productivity benefits of using LABS.GENERATIVEAI() in conjunction with LAMBDA-defined functions. These features build on our research in the Calc Intelligence team at Microsoft Research in Cambridge and arise from a long-term partnership with Excel

Reducing Errors in Excel Models with Component-Based Software Engineering
Craig Hatmaker
Model errors are pervasive and can be catastrophic. We can reduce model errors and time to market by applying Component-Based Software Engineering (CBSE) concepts to Excel models. CBSE assembles solutions from pre-built, pre-tested components rather than written from formulas. This is made possible by the introduction of LAMBDA. LAMBDA is an Excel function that creates functions from Excel’s formulas. CBSE-compliant LAMBDA functions can be reused in any project just like any Excel function. They also look exactly like Excel’s native functions such as SUM(). This makes it possible for even junior modelers to leverage CBSE-compliant LAMBDAs to develop models quicker with fewer errors.

A Use Case-Engineering Resources Taxonomy for Analytical Spreadsheet Models
Tom Grossman, Vijay Mehrotra
University of San Francisco
This paper presents a taxonomy for analytical spreadsheet models. It considers both the use case that a spreadsheet is meant to serve, and the engineering resources devoted to its development. We extend a previous three-type taxonomy, to identify nine types of spreadsheet models, that encompass the many analytical spreadsheet models seen in the literature. We connect disparate research literature to distinguish between an “analytical solution” and an “industrial-quality analytical spreadsheet model”. We explore the nature of each of the nine types, propose definitions for some, relate them to the literature, and hypothesize on how they might arise. The taxonomy provides guidance for where various spreadsheet development guidelines are most useful, provides a lens for viewing spreadsheet errors and risk, and offers a structure for understanding how spreadsheets change over time. This taxonomy opens the door to many interesting research questions, including refinements to itself.

How Beaufort, Neumann, and Gates met? Subject integration with spreadsheeting
Maria Csernoch, Julia Csernoch
University of Debrecen, Faculty of Informatics
Computational thinking should be the fourth fundamental skill, along with reading, writing, and arithmetic (3R). To reach the level where computational thinking skills, especially digital problem solving have their own schemata, there is a long way to go. In the present paper, a novel approach is detailed to support subject integration and building digital schemata, on the well-known Beaufort scale. The conversion of a traditional, paper-based problem and a data retrieval process are presented within the frame of a Grade 8 action research study. It is found that both students’ content knowledge and their digital skills developed more efficiently than in traditional course book and decontextualized digital environments. Furthermore, the method presented here can be adapted to any paper-based problems whose solutions would be more effective in a digital environment and which offer various forms for building schemata both in the subject matter and informatics.

Excel as a Turing-complete Functional Programming Environment
Peter Bartholomew
MDAO Technologies Ltd
Since the calculation engine of Excel was the subject of a major upgrade to accommodate Dynamic Arrays in 2018 there have been a series of seismic changes to the art of building spreadsheet solutions. This paper will show the ad-hoc end user practices of traditional spreadsheets can be replaced by radically different approaches that have far more in common with formal programming. It is too early to guess the extent to which the new functionality will be adopted by the business and engineering communities and the impact that may have upon risk. Nevertheless, some trends are emerging from pioneering work within the Excel community which we will discuss here.

ChatGPT and Excel – trust, but verify
Patrick O’Beirne
Systems Modelling Ltd
This paper adopts a critical approach to GPT-4, showing how its huge reach makes it a useful tool for people with simple requirements but a bad, even misleading guide to those with more complex problems which are more rarely present in the training data and even more rarely have straightforward solutions.
It concludes with a practical guide for how to add an Excelscript button, with system and user prompts, to the GPT-4 API into the Excel desktop environment, supported by a blog post giving the technical details for those interested.

Experimenting with ChatGPT3 for Spreadsheet Formulae Generation: The Risks of AI Generated Spreadsheets
Simon Thorne
Cardiff Metropolitan University
Large Language Models (LLM) have become sophisticated enough that complex computer programs can be created through interpretation of plain English sentences and implemented in a variety of modern languages such as Python, Java Script, C++ and Spreadsheets. These tools are powerful and relatively accurate and therefore provide broad access to computer programming regardless of the background or knowledge of the individual using them. This paper presents a series of experiments with ChatGPT to explore it’s ability to produce valid spreadsheet formulae and related computational outputs in situations where ChatGPT has to deduce, infer and problem solve the answer. The results show that in certain circumstances, ChatGPT can produce correct spreadsheet formulae with correct reasoning, deduction and inference. However, when information is limited, uncertain or the problem is too complex, the accuracy of ChatGPT breaks down as does its ability to reason, infer and deduce. This can also result in false statements and “hallucinations” that all subvert the process of creating spreadsheet formulae.

 

Click here to register


What are the Benefits of Attending the EuSpRIG Conference?

  • EuSpRIG is the only accessible source of relevant information on the subject
  • EuSpRIG attracts international expert speakers on the subject
  • EuSpRIG mixes academic and commercial interests, making us both forward looking & practical
  • EuSpRIG information is valuable ammunition in the battle to get the spreadsheet risks issue taken seriously within your organisation
  • EuSpRIG’s ideas are practical and implementable
  • EuSpRIG can demonstrate a track record of success
  • EuSpRIG is the only conference in its field that that you need to attend
  • EuSpRIG offers an opportunity to meet the regulator
  • EuSpRIG is an excellent forum for social & business networking
  • EuSpRIG provides a useful forum for earning CPD credits

We guarantee you’ll learn something useful if you come


Why Do People Attend The EuSpRIG Conference?

Comments from delegates attending the EuSpRIG 2011 conference were asked the question “Why are we here?”. All responses are reproduced below, unmodified and in order of receipt. Delegates could see each previous response on the questionnaire that was passed around. Dots represent unreadable.

  • I ask this question every day
  • To understand the almost impossible
  • To live and love with spreadsheets
  • Information, …, learning in -> commercial connections out
  • Find users of new risk-free technology
  • To understand the core issues of Spreadsheet Risk
  • To publish research
  • Paper has been accepted
  • To understand more about the dangers and how to minimise them
  • Update
  • To solve life’s great question:
    B2 or not B2
    =OR(B2, NOT(B2))
  • To get some feedback and see what the others are doing
  • To expand my understanding of the range of problems associated with modelling and model construction
  • To discover evil practices
  • Ideas with commercial potential, networking
  • Engaged in many consultancy projects involving spreadsheet systems. Would like to see what methodologies are used to aid these problems
  • 1) To show that we have a (possibly) unique take on spreadsheet layout/good practice & to share that knowledge 2) To network and gain contacts 3) To listen to what else is going on
  • To motivate the Spreadsheet Risk community to participate in the creation of a fully functional spreadsheet corpus for research and […]
  • Because its fun! Also because the world needs us…
  • To present my research, get some feedback and to know about real problems companies have.
  • To present research work, get feedback, share & collaborate. Network & build business partnerships
  • To learn more about the gaps between academic spreadsheet research and professional reality
  • To hear the above stories & to look for another job ?
  • Because I want to talk to people who understand why I get excited when I get my spreadsheets to work. Beats being in the office!
  • I got on the wrong train at London Bridge. I was meant to be in New York

How Can I Sponsor the Conference?

You can contact Patrick O’Beirne here