Figuring Out Why the Computer Rejected Your Loan Application
Machine-learning algorithms increasingly make decisions about credit, medical diagnoses, personalized recommendations, advertising and job opportunities, among other things, but exactly how usually remains a mystery. Now, new measurement methods developed by Carnegie Mellon University researchers could provide important insights to this process.
Was it a person’s age, gender or education level that had the most influence on a decision? Was it a particular combination of factors? CMU’s Quantitative Input Influence (QII) measures can provide the relative weight of each factor in the final decision, said Anupam Datta, associate professor of computer science and electrical and computer engineering.
“Demands for algorithmic transparency are increasing as the use of algorithmic decision-making systems grows and as people realize the potential of these systems to introduce or perpetuate racial or sex discrimination or other social harms,” Datta said.
“Some companies are already beginning to provide transparency reports, but work on the computational foundations for these reports has been limited,” he continued. “Our goal was to develop measures of the degree of influence of each factor considered by a system, which could be used to generate transparency reports.”
These reports might be generated in response to a particular incident — why an individual’s loan application was rejected, or why police targeted an individual for scrutiny, or what prompted a particular medical diagnosis or treatment. Or they might be used proactively by an organization to see if an artificial intelligence system is working as desired, or by a regulatory agency to see whether a decision-making system inappropriately discriminated between groups of people.
Datta, along with Shayak Sen, a Ph.D. student in computer science, and Yair Zick, a post-doctoral researcher in the Computer Science Department, will present their report on QIIat the IEEE Symposium on Security and Privacy, May 23–25, in San Jose, Calif.
Generating these QII measures requires access to the system, but doesn’t necessitate analyzing the code or other inner workings of the system, Datta said. It also requires some knowledge of the input dataset that was initially used to train the machine-learning system.
A distinctive feature of QII measures is that they can explain decisions of a large class of existing machine-learning systems. A significant body of prior work takes a complementary approach, redesigning machine-learning systems to make their decisions more interpretable and sometimes losing prediction accuracy in the process.
QII measures carefully account for correlated inputs while measuring influence. For example, consider a system that assists in hiring decisions for a moving company. Two inputs, gender and the ability to lift heavy weights, are positively correlated with each other and with hiring decisions. Yet transparency into whether the system uses weight-lifting ability or gender in making its decisions has substantive implications for determining if it is engaging in discrimination.
“That’s why we incorporate ideas for causal measurement in defining QII,” Sen said. “Roughly, to measure the influence of gender for a specific individual in the example above, we keep the weight-lifting ability fixed, vary gender and check whether there is a difference in the decision.”
Observing that single inputs may not always have high influence, the QII measures also quantify the joint influence of a set of inputs, such as age and income, on outcomes and the marginal influence of each input within the set. Since a single input may be part of multiple influential sets, the average marginal influence of the input is computed using principled game-theoretic aggregation measures previously applied to measure influence in revenue division and voting.
“To get a sense of these influence measures, consider the U.S. presidential election,” Zick said. “California and Texas have influence because they have many voters, whereas Pennsylvania and Ohio have power because they are often swing states. The influence aggregation measures we employ account for both kinds of power.”
The researchers tested their approach against some standard machine-learning algorithms that they used to train decision-making systems on real data sets. They found that the QII provided better explanations than standard associative measures for a host of scenarios they considered, including sample applications for predictive policing and income prediction.
Now, they are seeking collaboration with industrial partners so that they can employ QII at scale on operational machine-learning systems.
The Latest on: Making AI Decision-Making Accountable
via Google News
The Latest on: Making AI Decision-Making Accountable
- Algorithms: Public sector urged to be open about role in decision-makingon November 27, 2020 at 10:18 am
Public sector bodies must be more open about their use of algorithms in making decisions, ministers have been told. A government advisory body said greater transparency and accountability was needed ...
- How Apple Is Organized for Innovationon November 13, 2020 at 3:25 pm
As the importance of artificial intelligence and other new areas ... is essential for speedy and effective cross-functional decision-making at the highest levels. If managers attend a decision ...
- Use Of Algorithmic Decision Making & AI In Public Organisationson November 12, 2020 at 8:32 pm
A number of public organisations in several countries across sectors are now using data, AI and algorithms for decision-making processes.
- Concrete steps marketers should take now to get ready for CA’s CPRA in 2023on November 11, 2020 at 3:04 pm
It enables consumers (and employees) to opt-out of “automated decision making technology” (machine ... Most digital marketers are oblivious to the AI and ML advances in the marketing stack ...
- Proper implementation of chatbots in healthcare requires diligenceon November 10, 2020 at 10:57 pm
Many chatbots are powered by artificial intelligence. The paper specifically discusses ... The team believes they have laid out key considerations that can inform a framework for decision-making when ...
- 2020’s class of Top 30 under 30 sustainability leaders shape #nextnormalon November 9, 2020 at 9:51 am
“[Youth] continue to be marginalised in all forms of decision-making. It is absolutely imperative that we ... His journey in cleantech and AI began with an internship at the Clinton Global Initiative, ...
- Can AI eliminate bias in banks' hiring decisions?on November 6, 2020 at 12:43 pm
But the technology has its limits and is no replacement for human decision-making, experts say. In January, BOK deployed a conversational artificial intelligence assistant ... how they will hold ...
- The best artificial intelligence intentions are hitting corporate wallson October 31, 2020 at 7:25 am
Artificial intelligence and machine learning have ... ill-informed performance trade-offs and misalignment of incentives within decision-making structures that are only reactive to external ...
- What’s Next? Tech Platforms, Power, and Accountabilityon October 29, 2020 at 12:41 pm
Our decision-making processes have increasingly been given over to the ... This regulatory body could also enforce greater transparency around the data, algorithms, and AI databases that are ...
- Stop Overengineering People Managementon September 27, 2020 at 11:43 am
It treats labor as a commodity and seeks to cut it to a minimum by using automation and artificial intelligence ... wherein decision-making and control are pushed back to experts and algorithms.
via Bing News