Embracing data-driven law: SMU pioneers quantitative legal project

By Vince Chong

SMU Office of Research Governance & Administration – Imagine a popular hotel inundated by massive volumes of visitors year-round. Now imagine that it does not have the required technology or system to find out where most of them come from, or what they most like to do while staying there, the answers to which are essential to how it improves its operations. 

Singapore’s legal sector, alongside many other jurisdictions, faces the same quantitative quandary. While lawyers, researchers, and law students currently focus on individual laws and cases accessible through existing databases, none of the infrastructure cater to the empirical analysis of legal data in an age where digital data is exploding at pace.

The Singapore Management University’s Yong Pung How School of Law plans to change that with the Singapore Open Legal Informatics Database (SOLID) big data project. Led by Assistant Professor Jerrold Soh, the initiative is expected to be an open-source repository of quantitative legal data that provides accessible answers to data-driven legal questions. 

The Database, Professor Soh explained, could include data like the number of negligence cases decided by the Singapore courts in a specific year, and if they implied certain trends and patterns; the number of words on average in a court judgement, and if they are getting longer; as well as what kind of judgments tend to be more succinct than others.

“These are questions academic researchers like me are more likely to be curious about, but I can see practicing lawyers and perhaps policymakers may be interested in these things too as they provide a macro sense of how our legal system is doing,” Professor Soh told the Office of Research Governance & Administration (ORGA). 

One of SOLID’s key aims is to “promote Singapore law as a target of academic research and practical engagement,” according to the project proposal. Another is to create a detailed collection of statistical data on its legal system running all the way back to independence in 1965. The project is also expected to lower costs for academic and commercial research on Singapore law, while enabling data-driven legal insights.

The project team comprises mainly Professor Soh and Assistant Professor Dirk Hartung, alongside SMU research engineers and student assistants. It was launched in November 2025.

Data surge

As a free resource, SOLID arrives at a time where the increasing heft of Singapore law worldwide could likely motivate more empirical research on the same, Professor Soh said. Based on separate research that the academic and his co-authors are currently conducting, Singapore cases were cited close to 800 times by courts around the world in 2024. This compares with nearly none in the 1980s to 80 times in 2019. 

For the uninitiated, courts cite and take reference from foreign precedents to aid in their reasoning, particularly in common law systems such as Singapore, Malaysia, India, as well as England and Wales. The more a jurisdiction is cited, the more influential its rule of law is seen to be. 

“The recent 800 figure – a ten-fold increase – surprised me and I think this number will grow even without SOLID as the international recognition of our courts have been growing,” Professor Soh said. 

“Singapore law has been getting more influential – our very capable Supreme Court has been building strong international judicial networks and forging relationships with judiciaries around the world, for example in France, India, even the Middle East.”

It would be “nice,” he added, if a follow-up study on SOLID three to four years after completion found that the number of citations had grown even more, though “truthfully it would be difficult to isolate the cause of any increase”.

SOLID also comes at a critical juncture in terms of digital information accessibility. As the project team’s research showed – based on information captured by IDC and Statista – the volume of data, or information created, captured, copied and consumed globally spiked to 173.4 zettabytes in 2024, from two zettabytes in 2010. This is expected to more than triple to 527.5 zettabytes in 2029.

To put that in perspective, one zettabyte is one sextillion bytes – one followed by 21 zeroes – or 20 billion years of streaming Netflix shows.

“In a future where such data is more freely accessible, lawyers may slowly get used to including empirical data in their work,” Professor Soh said. 

“A recurrent bottleneck”

SOLID is set to complete over four phases, with the first involving consultation with stakeholders “to determine and identify valuable, credible, and practical data points”. The second phase focuses on data collection and extraction using methods including large language models, which is one form of AI. 

Phase Three will include data verification and the creation of a public website, while the last stage involves introducing the database and “co-developing use cases with other researchers and/or industry”. 

“When we get to this phase, we will be looking out for partners and collaborators on pragmatic applications,” project notes add.

The main goal of building SOLID, said Professor Soh, is to help “broadcast the quality, depth, accessibility, and future readiness of Singapore’s legal system”.

From a personal viewpoint, the project also represents the culmination of his own experiences of painstakingly building datasets; this goes back to when he was a law student who founded and ran a legal analytics setup.

“Across my startup and academic life, access to data was a recurrent bottleneck,” the researcher said, adding that it was not ideal since a legal system was supposed to be transparent. 

“Data gathering and collection took up a lot of time and resources. I realised then that a project like SOLID would not only make these tasks efficient and scalable, but also benefit the international legal community.” 

Back to Research@SMU May 2026 Issue