Edition: August 20th, 2021
Curated by the Knowledge Team of ICS Career GPS
- Excerpts from article by Tohid Atashbar, published on the World Economic Forum website (weforum.org)
Going by the current trends of artificial intelligence (AI) in economic modelling, sooner or later, technological unemployment will catch up with economists.
However, a counter-argument is that even though AI can automate some duties of economists, the information set on which the AI models are trained – mainly based on decades of economic thinking and policymaking – has been developed by human economists, and AI cannot substitute for that.
This critique might be valid about the traditional class of supervised AI machines in a limited computational capacity, but the new generation of AI models are different.
They can boundlessly search, iterate and artificially test the possible relations among the infinite set of variables, and can detect new relations or optimal policies. This will lead to the formation of a complete set of AI-developed theories.
AI Economists & AI Bias
The simplest application of AI economists would be to take on the main tasks that human economists carry out:
- Providing economic advice
- Answering economic questions
Here are some questions that were directed at an AI machine. These are the kind of questions a typical economist will need some time to think to answer:
(The answers were generated using OpenAI’s GPT-3)
Q1: What is the shortest path to economic development?
AI: There is no such thing as a shortcut. Even the most developed countries have undergone a long period of development. As China has been pursuing economic development for nearly three decades and taken one step at a time, it can be said that development is always a long-drawn-out process.
Q2: Should robots receive Universal Basic Income?
AI: Alas, the question is not clear. For if to be given money is a right, then the right must be universal. To be universal the right must belong to everyone, including robots. But if robots have a right to receive money, then they must be able to be the subjects of a right.
One may think that the above answer has embedded bias in it, a phenomenon all current AI frameworks suffer from in different ways.
Q3: Is wealth tax effective in reducing inequality?
AI: No, it is not. The most important reason for this is that high income earners are much more mobile than the majority of the population. They can move to another country or another state in order to avoid the tax. If you want to tax the rich, you have to have a global tax.
AI Economists will be biased just like Human Economists
Currently, AI machines are susceptible to bias against or toward theories. The two main sources of AI bias are similar to those behind human cognitive bias:
- Bias in the inputs (information and data)
- Bias in the methodology of looking at the data (algorithm).
As economists might obtain different results depending on their methodological preferences when looking at the same or different data, robots will also obtain different results depending on the literature or information they are fed.
This bias can be managed or limited, but it cannot be avoided completely.
Concerns & Solutions
- AI machines cannot distinguish between theories and apply them to data to evaluate how theory and data match up
- This may further limit the interpretability or application of such models.
- This critique is called theoretical blindness.
- The fact that unsupervised and reinforcement learning machines allow the model to work on its own to discover / test patterns that were previously undetected, without a need for a supervisor, could lead to a more efficiency-based non-partisan economics.
- If bias is unavoidable, an interim practical approach might be transparently labeling, ranking or classifying machines based on bias in their output.
(Disclaimer: The opinions expressed in the article mentioned above are those of the author(s). They do not purport to reflect the opinions or views of ICS Career GPS or its staff.)