Costello Research Artificial Intelligence

George �鶹��Ƶ researcher is using AI to identify human trafficking hot spots

Katelynn C Hipolito — Mon, 29 Sep 2025 18:20:46 +0000

George �鶹��Ƶ researcher is using AI to identify human trafficking hot spots Katelynn C Hipolito Mon, 09/29/2025 - 14:20

Illicit massage businesses (IMBs) run by human trafficking rings are rampant in the United States. A �鶹��Ƶ professor has helped build what may be the best artificial intelligence (AI)-driven tool to root them out.

Human trafficking rings are at their most dangerous when they masquerade as legitimate commercial activity. IMBs are one of the most common ways in which exploitive networks operate in plain sight.

The Network, an anti-trafficking nonprofit, estimates that there are more than 13,000 IMBs active in the United States, raking in annual total revenue of more than $5 billion.

Abhishek Ray

“You are stuck in a massage business. You’re not allowed to go out,” says Abhishek Ray, assistant professor of information systems and operations management at the Donald G. Costello College of Business at George �鶹��Ƶ, describing the plight of IMB workers. “Your passports are taken away, and you’re supposed to do a certain amount of business every day and give the money to the trafficker. It’s a really abhorrent form of abuse.”

Ray is one of a growing group of researchers exploring how various forms of AI could help resource-constrained law enforcement agencies differentiate between IMBs and the legitimate enterprises they try to mimic. His ongoing research using graph neural networks has yielded more promising results than rival approaches, when put to the test in a recent experiment.

His co-researchers on the IMB project are Lumina Albert and Swetha Varadarajan of Colorado State University.

According to Ray, “Graph neural networks are just a fancy way of saying that if I get a graph of a city or locality at one point in time, and I add data to it, can I predict future patterns on this graph if I know the past?”

This approach made sense for detecting IMBs, because try as they might to appear above board, they have geographical needs that conventional businesses don’t. “IMBs don’t allow their trafficked employees to go out of the parlor,” Ray says. “But since they’re humans, they need sustenance. They have to be near groceries, gas stations, where they can get stuff and come back.”

The researchers combined several graph neural networks into a framework called IMBWatch. The training data-set for IMBWatch comprised publicly available information such as online customer reviews, arrest and raid data for known IMBs, and advertisements from websites promoting illicit activities (e.g., the infamous Backpage). The result, in essence, was a series of snapshots mapping the evolution of the IMB network in a given city or county over a period of time. This could then be overlaid on geographical maps to tease out hidden patterns.

To gauge IMBWatch’s relative performance, the researchers let it loose on a testing data-set alongside four other AI models, which were not as sensitive to the nuanced interplay of spatial and temporal factors. Of the five models, IMBWatch provided the most accurate, precise and informative predictions. In other words, it outperformed the others at spotting IMBs among a larger mass of local businesses.

While encouraging, these outcomes require further confirmation with a larger data-set. “IMBWatch was trained on data from Georgia and Louisiana, not the entire United States,” Ray says. “These were small, manageable data-sets, but we will now scale up to major states such as New York and California.”

The researchers are also looking at enhancing IMBWatch with data related to how workers end up wandering into trafficking webs. These might include “proximity to hospitals, religious places, etc. because a lot of times people are coerced by religious compulsions, or because they’re pregnant and need some care,” Ray says.

This is not Ray’s first foray into the field of AI-fueled anti-trafficking. Previously, Ray co-developed a model for improving machine learning-based detection of human trafficking activity at transit stations and on fishing vessels.

However, law enforcement agencies and other pertinent stakeholders (e.g., business owners) are often wary of adopting AI-based solutions, due to a lack of trust in the technology. Ray and his co-researchers are currently devising a framework that will clarify how these stakeholders can work together with tech experts and, perhaps most importantly, human trafficking survivors to make the best possible use of AI.

“This qualitative piece is required to make sure that people who are on the sidelines, on the fences about using this actually start using it, because that’s the need right now,” Ray says.

Learn more about Artificial Intelligence at George �鶹��Ƶ

In This Story

Abhishek Ray

Topics

A.I. and Innovation - Costello

Research

ESG - Costello

Artificial Intelligence

Costello Research Artificial Intelligence

Costello Research Machine Learning

Costello Research Data Analytics

Costello Research Sustainable Operations

Costello College of Business News

Costello College of Business Faculty Research

Information Systems and Operations Management Area

Nonprofits are in trouble. Could more sensitive chatbots be the answer?

Jennifer Anzaldi — Tue, 18 Mar 2025 14:48:25 +0000

Nonprofits are in trouble. Could more sensitive chatbots be the answer? Jennifer Anzaldi Tue, 03/18/2025 - 10:48

In today’s attention economy, impact-driven organizations are arguably at a disadvantage. Since they have no tangible product to sell, the core of their appeal is emotional rather than practical—the “warm glow” of contributing to a cause you care about. But emotional appeals call for more delicacy and precision than standardized marketing tools, such as mass email campaigns, can sustain. Emotional states vary from person to person—even from moment to moment within the same person.

Photo by Getty Images

Siddharth Bhattacharya and Pallab Sanyal, professors of information systems and operations management at the Donald G. Costello College of Business at �鶹��Ƶ, believe that artificial intelligence (AI) can help solve this problem. A well-designed chatbot could be programmed to calibrate persuasive appeals in real time, delivering messaging more likely to motivate someone to take a desired next step, whether that’s donating money, volunteering time or simply pledging support. Automated solutions, such as chatbots, can be especially rewarding for nonprofits, which tend to be cash-conscious and resource-constrained.

“We completed a project in Minneapolis and are working with other organizations, in Boston, New Jersey and elsewhere, but the focus is always the same,” Sanyal says. “How can we leverage AI to enhance efficiency, reduce costs, and improve service quality in nonprofit organizations?”

Siddarth Bhattacharya. Photo provided

Sanyal and Bhattacharya’s working paper (coauthored by Scott Schanke of University of Wisconsin Milwaukee) describes their recent randomized field experiment with a Minneapolis-based women’s health organization. The researchers designed a custom chatbot to interact with prospective patrons through the organization’s Facebook Messenger app. The bot was programmed to adjust, at random, its responses to be more or less emotional, as well as more or less anthropomorphic (human-like).

“For the anthropomorphic condition, we introduced visual cues such as typing bubbles and slightly delayed response to mimic the experience of messaging with another human,” Sanyal says.

The chatbot’s “emotional” mode featured more subjective, generalizing statements with liberal use of provocative words such as “unfair,” “discrimination” and “unjust.” The “informational” modes leaned more heavily on facts and statistics.

Over the course of hundreds of real Facebook interactions, the moderately emotional chatbot achieved deepest user engagement, as defined by a completed conversation. (Completion rate was critical because after the last interaction, users were redirected to a contact/donation form.) But when the emotional level went from moderate to extreme, more users bailed out on the interaction.

The takeaway may be that “there is a sweet spot where some emotion is important, but beyond that emotions can be bad,” as Bhattacharya explains.

Pallab Sanyal. Photo provided

When human-like features were layered on top of emotionalism, that sweet spot got even smaller. Anthropomorphism lowered completion rates and reduced the organization’s ability to use emotional engagement as a motivational tool.

“In the retail space, studies have shown anthropomorphism to be useful,” Bhattacharya says. “But in a nonprofit context, it’s totally empathy-driven and less transactional. If that is the case, maybe these human cues coming from a bot make people feel creepy, and they back off.”

Sanyal and Bhattacharya say that more customized-chatbot experiments with other nonprofits are in the works. They are taking into careful consideration the success metrics and unique needs of each partner organization.

“Most of the time, we researchers sit in our offices and work on these problems,” Sanyal says. “But one aspect of these projects that I really like is that we are learning so much from talking to these people.”

In collaboration with the organizations concerned, they are designing chatbots that can cater their persuasive appeals more closely to each context and individual interlocutor. If successful, this method would prove that chatbots could become more than a second-best substitute for a salaried human being. They could serve as interactive workshops for crafting and refining an organization’s messaging to a much more granular level than previously possible.

And this would improve the effectiveness of organizational outreach across the board—a consummate example of AI enhancing, rather than displacing, human labor. “This AI is augmenting human functions,” says Sanyal. “It’s not replacing. Sometimes it’s complementing, sometimes it’s supplementing. But at the end of the day, it is just augmenting.”

In This Story

Siddharth Bhattacharya

Pallab Sanyal

Topics

A.I. & Innovation - Costello

ESG - Costello

Costello Research Digital Platforms

Costello Research Artificial Intelligence

Costello Research Machine Learning

Costello College of Business News

Costello College of Business Faculty Research

ISOM Faculty Research

Research

Artificial Intelligence

How machine learning improvements are helping to fight human trafficking

Marianne Klinker — Wed, 22 Feb 2023 13:09:33 +0000

How machine learning improvements are helping to fight human trafficking Marianne Klinker Wed, 02/22/2023 - 08:09

Human trafficking is a global crisis of overwhelming scope. Fortunately, anti-trafficking organizations can use AI to predict the criminals’ next moves–with the help of a �鶹��Ƶ professor.

The fight against human trafficking has a David and Goliath aspect to it. Trafficking rings are a global scourge with an estimated 25 million victims and $150 billion in annual profits. Agencies and NGOs tasked with stopping the traffickers, however, are typically small and under-resourced. Recently, a technological tool has come along to help close this gap–machine learning (ML) algorithms.

Primed with enough relevant data, these algorithms can find hidden clues to how traffickers operate and what they are likely to do in the future. In principle, anti-trafficking agencies can use ML predictions to direct their scant resources to the areas of greatest risk.

Abhishek Ray

Abhishek Ray, an assistant professor in the Information Systems and Operations Management area at the �鶹��Ƶ School of Business, has added his expertise to this effort. With collaborators Viplove Arora (post-doc researcher at SISSA, Italy), Kayse Maass (of Northeastern University) and Mario Ventresca (of Purdue University), Ray developed a model that reduces the guesswork of implementing ML predictions.

As Ray explains it, the model supplies a “layer on top” for improving outcomes of existing ML solutions. Armed with success and failure rates (i.e., true/false negatives and positive trafficking detections) of an anti-trafficking agency, it looks for scenarios in which the agency could achieve the same number of successes with fewer errors.

In a recently published paper, Ray and his co-authors apply their model to two real-life agencies: Global Fishing Watch (GFW), which targets trafficking in the global seafood industry, and Love Justice International (LJI), which monitors transit stations on the India-Nepal border.

The ML solution employed by GFW cross-references a large database of fishing vessel activity, which is obtained via satellite, with law enforcement data on human trafficking. The resulting predictions indicate the vessel types, behaviors, and features that the agency should watch most closely.

But criminals sometimes learn faster than machines. “If someone is caught on a long trawler, and they know they can get caught, they will never go on the long trawler again,” Ray explains. Traffickers’ evolving tactics may not be fully captured in vast, wide-ranging data-sets, such as the ones derived from satellite vessel surveillance. Changes in agency success rates, on the other hand, are closer to the action and may pick up the latest stages of this cat-and-mouse game.

Looking back over agency data from 2012-2018, the researchers found that had their model been used alongside Machine Learning, the agency Global Fishing Watch would likely have discovered more instances of trafficking while committing far fewer false negatives and false positives.

Looking back over agency data from 2012-2018, the researchers found that had their model been used alongside ML, GFW would likely have discovered more instances of trafficking while committing far fewer false negatives and false positives. In addition, monitoring recommendations shifted considerably over the six years. For example, under certain conditions, drifting longline vessels were the most likely suspects for the years 2012-2017. In 2018, however, squid jiggers replaced them and were singled out as among the most suspicious. These shuffling priorities may reflect the traffickers’ changing their vessel of choice to evade detection.

In the case of Love Justice International, Ray’s model could serve as a workaround for constraints such as a shortage of well-trained staff. LJI could input a target outcome into the algorithm, such as a baseline number of positive trafficker IDs, and receive recommendations for how to make the best use of strained resources.

For Ray, the fight against human trafficking is personal. As a child growing up in Kolkata, India, he was cared for by a household employee who, as his parents later found out, had been trafficked when she herself was a child. “I learned this when I was doing my PhD in the U.S.,” he says. “It’s like having a part of your childhood taken away. You came into contact with something criminal and had no understanding.”

“If I could make a contribution towards solving the problem, I’d consider it sort of giving back what I had taken unknowingly.”

To take full advantage of Ray’s “layer on top” ML solution, anti-trafficking agencies would need to create effective systems for collecting and centralizing data. Depending on the context, this might present challenges ranging from resource limitations to a political climate where trafficking data could be used against the already-victimized. “The maximum value from our framework is when it’s acting in real time with real-time data,” Ray says.

Topics

A.I. & Innovation - Costello

Costello Research Artificial Intelligence

Costello Research Machine Learning

Costello Research Data Analytics

ESG - Costello

Costello Research Cybersecurity

Costello College of Business News

Costello College of Business Faculty Research

Tech Talent Investment Program

Research

Artificial Intelligence

More School of Business Faculty Research

The hidden cost of environmental policy uncertainty
October 24, 2025
George �鶹��Ƶ marketing professor receives prestigious research funding
October 10, 2025
‘Nothing to see here’: How corporate spin confuses Wall Street
October 8, 2025
Costello College of Business welcomes eight new research-focused faculty
October 1, 2025
George �鶹��Ƶ researcher is using AI to identify human trafficking hot spots
September 29, 2025

In This Story

Abhishek Ray

Building a 'digital twin' of the real world

Jennifer Anzaldi — Mon, 26 Sep 2022 14:02:39 +0000

Building a 'digital twin' of the real world Jennifer Anzaldi Mon, 09/26/2022 - 10:02

In This Story

Jingyuan Yang

As artificial intelligence (AI) has become more adept at anticipating people’s wants and needs, predictive algorithms have been mingled with almost everything we do digitally. When we are done watching a Netflix show, they take the liberty of queueing up the next one—they finish our sentences in Outlook and Gmail.

Jingyuan Yang

In the offline world, however, the complex and multidimensional nature of many of our most pivotal decisions defies algorithmic analysis. That is, unless AI can learn to detect how real-world contingencies, such as specifics of time and place, govern our choices.

Jingyuan Yang, an assistant professor of information systems and operations management at �鶹��Ƶ School of Business, is at the forefront of AI research that aims to crack the codes of the physical world. Her results so far point toward innovative solutions for some of the biggest societal, governmental, and business challenges we face.

Several of her papers to date investigate urban bike sharing, a “last mile” extension of public transport systems designed to coax commuters out of their cars. Some early adopters of bike sharing, such as New York City and Taiwan, have seen long-term success with the model. But elsewhere, including major Chinese cities, oversaturation has led to bicycle-flooded sidewalks or, even worse, rivers and vacant lots turning into bicycle graveyards—an environmental disaster that produced friction with local politicians.

Yang discovered that in Shanghai, part of the problem was that the distribution of bikes across the city did not match demand. Some areas had far more available bikes than riders, while in others the opposite was the case. Additionally, Shanghai’s system allowed commuters to dismount wherever they chose. This dockless model made predicting rider demand even more challenging, as bikes could be located virtually anywhere.

With a team of six other researchers[1], Yang developed a data-driven model for predicting traffic flows within dockless bike-sharing systems, based on a dataset provided by leading provider Mobike. Spanning the period February 2017-March 2018, the Mobike data contained more than 957 million riding records from nearly 315,000 shared bikes.

The research team extracted flow patterns from the data by partitioning the city and “smoothing out” areas with the lowest levels of activity. The resulting grid-like “flow matrix” carved Shanghai’s bike traffic into spatio-temporal snapshots that could be studied and compared. After clustering these based on their similarities, the researchers could construct “base matrices” that provided broader, deeper points of reference for prediction than temporal or geographic cues alone. Using the base matrix, the algorithm could identify emergent patterns in a certain area as those associated with central business districts on a rainy holiday morning and forecast bike traffic in that area over the next few hours accordingly.

Yang says she was surprised by what this technique of algorithmic mapping revealed. “There are a number of surprising factors we can discover that cannot be covered by traditional model analysis. As an example, we find that there is a slight increase in bike traffic near subway stations during rain, because people want a shorter commute,” she says.

The team tested their model against six other algorithms designed for the same purpose, to see which was the most accurate at predicting actual bike traffic flow in Shanghai. Yang’s team’s solution consistently outperformed the rest on sample datasets for regular working days, rainy working days and holidays–meaning it achieved the lowest degree of prediction error. Perfect predictions are impossible, because all sorts of irregular real-world occurrences, from auto accidents to one-off public events, can cause traffic on a given day to break with the pattern. “Really odd events, we cannot capture,” Yang says. “But the base matrix lets us capture basic trends.”

For Yang, optimizing bike sharing is part of a necessary push toward environmentally sustainable options for urban living, including fewer polluting modes of transport. “All these papers are intended to help companies go a more sustainable way and help the user to tackle the last mile in an eco-friendly manner-without waste and damage to the environment.”

With some tweaks to the logic, however, the same AI-based methods can apply to a range of pressing business issues. The territory mapped by algorithms need not be geographical; researchers can also “map” a network of individuals or companies. Yang’s experiment in the field of B2B marketing is a case in point. She helped build[2] an automatic recommendation engine for marketing campaigns based on customer profiles (similar in concept to the bike-sharing base matrices) reflecting corporate affiliation as well as individual employee status. Customers from the same “region” on the grid, i.e. the same company, are treated holistically to improve recommendation quality.

“When you’re selling to a company, you’re usually dealing with a group of decision-makers who are at different buying stages," Yang explains. "To estimate buying propensity, you need to consider that they may share information. Their behavior should be considered together. Therefore, we use matrix representation to extract their shared knowledge.”

One of Yang’s current research projects focuses on predicting employee flow within networks of companies, again borrowing spatio-temporal techniques. Similar to Shanghai’s urban environment, the job-hopping professional grid has its own version of “weather”—favorable or gloomy economic conditions – that may alter the pattern.

“Based on different job positions, you can group the companies. You can aggregate company profiles and predict, collectively, how many people will leave based on the stock price,” she says.

Yang’s research suggests that by building a chessboard-like “digital twin” of the real world, spatio-temporal AI solutions can help business and society predict–and thus prevent–harmful losses such as human capital flight and damage to the natural environment.

[1] Jingjing Gu, Qiang Zhou and Yanchao Zhao (of Nanjing University of Aeronautics and Astronautics), Yanchi Lui and Hui Xiong (of Rutgers University), Fuzhen Zhuang (of Chinese Academy of Sciences)

[2] In collaboration with Chuanren Liu (of Drexel University), Mingfai Teng and Hui Xiong (of Rutgers University) and Ji Chen (Google).