Promise of IRSHAD: The Intelligent Robo Shariah Advisor

In one of my earlier blogs, I had proposed a model on the use of artificial intelligence to undertake a valuation of waqf assets based on publicly available information. I am glad to note that IBF DigiLabs has now operationalized this model for India and plans to repeat the same for Indonesia. It is also working on another project with similar methodology to identify and classify zakat beneficiaries (mustahiq). With some brilliant data scientists and knowledge engineers at work, its newly set up AI Lab is now buzzing with activities, alhamdulillah.

What I am going to talk about today is another project with great promise. It is about an Intelligent Robo Shariah Advisor (IRSHAD). The term Irshad implies guidance or the guiding hand. In line with this connotation, Irshad is a system that emulates, or acts in all respects, with the advisory and guidance capabilities of a human Shariah Advisor. The system in different phases of development seeks to be functionally equivalent to an Islamic legal expert in tackling specific problem domains of reasonable complexity. Irshad should don the hat of a Zakat Advisor soon, according to knowledge engineers at IBF DigiLabs, sometime around mid-Sha’ban, when most zakat organizations launch their Ramadhan mobilization drive. It will offer a channel of communication with potential zakat payers through which the latter can seek guidance regarding their zakat liability accompanied by explanations and how best to pay the zakat due.

Another module of Irshad will be about Islamic wills and inheritance. Muslims can seek guidance regarding how best they should distribute their wealth and assets in accordance with the Shariah. This is extremely valuable especially for people living in Muslim-minority countries where the laws of intestacy are not based on Shariah. In these countries, it is important to have a will in conformity with Shariah, else, the assets of a deceased Muslim will be distributed according to domestic law, not Islamic law.

The next module proposed under Irshad is no less ambitious. It will transform Irshad into a wise Investment Advisor for socially responsible Islamic organizations and financial institutions seeking to operationalize the SDGs in the light of the Maqasid Al-Shariah. In addition to risk and expect return from investments, the impact – environmental and social on the people and the planet – of investment decisions has long been globally recognized as a major governing factor. At the same time, it poses serious measurement challenges, even today. The challenge is far greater for Islamic financial institutions and markets as well as Islamic non-profit organizations and waqf-based institutions, who must consider yet another dimension, the Maqasid-al-Shariah (MaS) in their investment decisions. I deem it a privilege to be part of the solution, inshaAllah, when Irshad is able to crack this problem with its machine-enhanced capabilities. And Irshad should of course, be able to tackle the routine Shariah-legal matters in Islamic finance with an extended mandate. 

What kind of technology will drive Irshad? Given the deterministic nature of Shariah rules, the initial version of Irshad will essentially be an expert system that will use rule-based programming. The knowledge base for engineering the rules will be created by using AI-based text-analysis of relevant literature and data. While the scarcity of literature and relevant data on practical implementation of MaS is generally a constraint for developing solutions in this area, IBF Net should be able to address the challenges with its years of in-house research work in related areas. It has in the past undertaken extensive research into the degree of alignment (or otherwise) between the Sustainable Development Goals (SDGs) and the goals of Shariah (MaS). It has also undertaken comprehensive surveys on how such objectives have shaped the programs and projects of Islamic non-profits (and awqaf) historically and in the present times. Such data and information will form the basis of knowledge engineering for Irshad. Irshad will also use NLP tools for translation and text-to-speech capabilities. The subsequent modules of Irshad as an investment advisor would make use of real-time data and more dynamic AI-based models.

Why do we need to create an artificially intelligent Shariah expert, if a human expert can solve the same problem?

Some answers to this question may be rooted in behavioral factors. Human Shariah experts are expected to be available for consultation only during stipulated hours or time periods. Irshad will be available 24/7 with high reliability. Humans experts are vulnerable to behavioral idiosyncrasies, may display cognitive or other forms of bias or even logical fallacies. Human experts may not make themselves available in hostile and hazardous environments. Irshad will be immune to any fear factor. Irshad will essentially clone the experts. It would explain the reasoning without bias or attitude. Irshad will not forget, while human experts may. Human experts are influenced by recency effects (most recent information having a disproportionate impact on judgment). They are also influenced by primacy effects (early information dominates the judgment). Irshad will be free from such effects. Irshad will be consistent. It will handle similar transactions in the same way. It will make comparable recommendations for like situations.

Will Irshad increase efficiency in terms of costs? Irshad can be cloned easily without any upper limit on reproduction. One can make multiple copies of its system with further customization if required, while training new human experts is usually time-consuming and expensive. Although the Irshad system may be expensive to build and maintain, it will be inexpensive to operate. Its development and maintenance costs can be spread over many users. Will Irshad increase efficiency in terms of better analysis of complex rules and improved decisions? If there is a maze of rules (as usually the case with Shariah), then the Irshad system can unravel the maze with greater diligence. Human expertise in such cases is likely to be scarce and costly.

A computer-based system like Irshad can provide permanent documentation of the decision process. It will do a better job in terms of completeness. It can review all the transactions, while a human expert can only review a sample. It can produce more timely results, faster decisions and better prevent fraud and/or errors. Most importantly, it will use cutting-edge knowledge and combined wisdom of multiple human Shariah experts.

Irshad will have a few limitations to begin with. However, it will learn to acquire more and more artificial intelligence as it increasingly interacts with humans. It may not be able to respond creatively to unusual situations. And of course, it will fail to produce an answer when the problem is outside its area of expertise. Notwithstanding these limitations, the promise of Irshad has proved to be irresistible. Among the maiden users of the initial module of Irshad will be the zakat organizations engaged in the mobilization of zakat and sadaqah and the large number of zakat payers during this Ramadhan inshaAllah. It is this thought that propels the young and talented engineers and programmers at IBF DigiLabs.