AI is here and in the words of PF Sloane many think, we are on the “the eve of destruction.” But it is not that dire, it always feels this way when we are on “the eve of disruption”. For example:
- 100 years ago, Kodak fiends were roaming the country taking pictures without permission, considered an invasion of privacy and pursued legal recourse to prevent this activity.
- “Where a calculator on the ENIAC is equipped with 18,000 vacuum tubes and weighs 30 tons, computers in the future may have only 1,000 vacuum tubes and weigh only 1.5 tons.” Popular Mechanics, 1946.
- Twenty years after television’s invention, in 1946 Darryl Zanuck stated, ”people will soon get tired of staring at a plywood box every night.”
- The cell phone was viewed as having no viable future. Marty Cooper, known as the father of the cell phone, “cellular phones will absolutely not replace local wire systems,” “Even if you project it beyond our lifetimes, it won’t be cheap enough.”
The artificial intelligence disruption is rolling in and protesting or lamenting the risks will not hold it back. In these situations, big opportunities come commensurate with risks and responsibilities. Minimizing the challenges confronting this generation, present significant leadership moments. So, we have been here before, the next wave is approaching, and disaster is just around the corner. What is different is the reach of artificial intelligence.
The artificial intelligence wave is here, perhaps not cresting yet and what are some of the most frequently presented concerns?
- It’s The Wild West Out There – As invasive as artificial intelligence can be, standards (pgs. 18 & 19) for testing and ethics are at best emerging.
- Man + Machine – trusting the outputs is an increasing concern considering all of the artificial applications and further complicates increasing machine and software addiction.
- Judgment – intelligent machines require context from humans to complete tasks. This results in a single-mindedness in completing the task. If there is conflict or roadblock in completing the tasks will it make the right call or violate Issac Assimov’s laws?
- Control – Humans, who are limited by slow biological evolution, couldn’t compete and would be superseded,” Prof Stephen Hawking. How do humans guide artificial intelligence innovation without losing control.
- We Don’t Have All The Answers – as machines intelligence grows what are plans to monitor the algorithms and learning ability and have standards, ethics and tracking to control and isolate and fix issues.
These are some of the challenges with artificial intelligence, but not a complete list.
The challenges are but the opportunities are significant. They include:
- Predictive maintenance for automobiles and capital equipment (glass furnaces, paint systems)
- Packaging recommendations for eCommerce deliveries reducing transportation cost and waste
- Fraud prevention for credit card usage and online recommendations
- Logistics support in assessing traffic flows and optimizing transportation routes
- New drug creation leveraging historical data and medical intelligence
It is hard to imagine a discipline where artificial analysis has greater impact than marketing. Areas affected include:
- Personalization of the customer experience: social media, email, eCommerce, and notifications
- Monitoring and enhancing delivery of paid ad campaigns
- Improving the content and context of content creation using natural language processing and sentiment analysis
- Intelligent chatbots delivering human-like performance during online customer interactions
- Anticipating churn and focusing content and notifications to re-engage customers
- Showcasing products and/or services based on customer interactions with enterprise
With all the avenues for delivery business value, it is little wonder that artificial intelligence is projected to deliver additional global output of $13 trillion dollars.
Where We Go From Here
The value proposition is extensive, at the same time, the risk profile can be viewed as daunting. Where we go from here?
Management the introduction of artificial intelligence must address risk areas mentioned earlier. The risk/reward relationship has all of the elements associated with introducing any new technology. Artificial intelligence intensifies the risk/rewards because we are replacing routine human tasks and/or introducing data relationships and business tasks not easily grasped or described.
Not understanding all the outcomes after implementation impacts the ability to have a sense of risk profiles for each potential application. Prevention and second order thinking becomes critical in assessing unintended consequences. It starts with the technology used to implement solutions powered by artificial intelligence. Isolating, cleansing and appropriate unstructured data use from a variety of sources is an emerging challenge. This must be in in a secure manner, without revealing sensitive and personal information and still achieve the business value of the algorithm/model. The delivery of the right data at the right time along with the uptime of the infrastructure of the solution is also key when artificial intelligence is applied to a mission critical functions, like customer service. Additionally, for what appears like non-sensitive information in building the artificial intelligence solution must have appropriate security levels so that bad actors are prevented from building false identities.
If an artificial intelligence solution could be compared to an automobile, the above elements would be similar to the frame, body, and tires/brakes. The real “engine” is the algorithm. In building and maintaining the algorithm constant vigilance is required to ensure that recommended outcomes are consistent with regulations, social norms, and brand image. Managing the supplied data and supervising the algorithm must address concerns over bias, underrepresented populations, and outcomes where there is no recourse (outcomes where it is unknown how to change the recommendation). Outcomes and responding to them also require consideration how the solution interacts with humans. When and how do humans interact with solutions when the solutions are slow to react to or are generating safety issues. This is not straightforward because they must also address situations where human judgment may be incorrect.
When implementing artificial intelligence, the following quote comes to mind:
“Where there is great power there is great responsibility,” Winston Churchill 1906
In meeting challenges artificial intelligence presents, a structured enterprise approach isolating the most critical risks, controls for development/implementation of solutions and strategy that prioritizes risks based on model transparency, complexity, and the nature of the human interface.