arXiv subjects

Iman Dayarian

Publications and source records attributed to Iman Dayarian.

3 recordsLinked to original sources

arXiv2026

Hidden in Plain Sight: Detecting Illicit Massage Businesses from Mobility Data

Illicit massage businesses (IMBs) masquerade as legitimate massage parlors while facilitating commercial sex and human trafficking. Law enforcement must identify these businesses within a dense population of lawful establishments, but investigative resources are limited and the illicit status of each location is unknown until inspection. Detection methods based on online reviews offer some insight, yet operators can manipulate these signals, leaving covert establishments undetected. IMBs constitute one of the largest segments of indoor sex trafficking in the United States, with an estimated 9,000 establishments. Mobility data offers an alternative to online signals, covering establishments that avoid digital visibility entirely. We derive features from mobility data spanning temporal visitation patterns, dwell times, visitor catchment areas, and demand stability. Because confirmed labels exist only for establishments identified through advertising platforms, we employ positive-unlabeled learning to address the label asymmetry in ground truth. The model achieves 0.97 AUC and 0.84 Average Precision. Four operational signatures characterize high-risk establishments: demand consistency, evening-concentrated visits, compressed service durations, and locally drawn clientele. The model produces risk scores for each business-week observation. Aggregating to the business level, prioritizing the highest-risk 10% of massage establishments captures 53% of known illicit operations, a 5.3-fold improvement over uninformed inspection. We develop a decision-support system that produces calibrated prioritization scores for law enforcement, enabling investigators to concentrate inspections on the highest-risk venues. The operational signatures may resist strategic manipulation because they reflect actual operations rather than online signals that operators can control.

cs.CY↗

arXiv2023

A branch-cut-and-price algorithm for a dial-a-ride problem with minimum disease-transmission risk

This paper investigates a variant of the dial-a-ride problem (DARP), namely Risk-aware DARP (RDARP). Our RDARP extends the DARP by (1) minimizing a weighted sum of travel cost and disease-transmission risk exposure for onboard passengers and (2) introducing a maximum cumulative exposure risk constraint for each vehicle to ensure a trip with lower external exposure. Both extensions require that the risk exposure of each onboard passenger is propagated in a minimized fashion while satisfying other existing constraints of the DARP. To fully describe the RDARP, we first provide a three-index arc-based formulation and reformulate the RDARP into an equivalent min-max trip-based formulation, which is solved by an exact Branch-Cut-and-Price (BCP) algorithm. For each node in the branching tree, we adopt the column generation method by decomposing the problem into a master problem and a subproblem. The latter takes the form of an elementary shortest path problem with resource constraints and minimized maximum risk (ESPPRCMMR). To solve the ESPPRCMMR efficiently, we develop a new labeling algorithm and establish families of resource extension functions in compliance with the risk-related resources. We adopt a real-world paratransit trip dataset to generate the RDARP instances ranging from 17 to 55 heterogeneous passengers with 3 to 13 vehicles during the morning and afternoon periods. Computational results show that our BCP algorithm can optimally solve all small- and medium-sized instances (32 or fewer passengers) within 5 minutes. For the large instances (39 to 55 passengers), our BCP algorithm can solve 23 of 30 instances optimally within a time limit of one hour.

math.OC↗

arXiv2019

Learning to Project in Multi-Objective Binary Linear Programming

In this paper, we investigate the possibility of improving the performance of multi-objective optimization solution approaches using machine learning techniques. Specifically, we focus on multi-objective binary linear programs and employ one of the most effective and recently developed criterion space search algorithms, the so-called KSA, during our study. This algorithm computes all nondominated points of a problem with p objectives by searching on a projected criterion space, i.e., a (p-1)-dimensional criterion apace. We present an effective and fast learning approach to identify on which projected space the KSA should work. We also present several generic features/variables that can be used in machine learning techniques for identifying the best projected space. Finally, we present an effective bi-objective optimization based heuristic for selecting the best subset of the features to overcome the issue of overfitting in learning. Through an extensive computational study over 2000 instances of tri-objective Knapsack and Assignment problems, we demonstrate that an improvement of up to 12% in time can be achieved by the proposed learning method compared to a random selection of the projected space.

stat.ML↗