arXiv subjects

Sajid Siraj

Publications and source records attributed to Sajid Siraj.

5 recordsLinked to original sources

arXiv2026

Detecting Deceptive Recruitment: A Signal-theoretic Machine Learning Framework for Early Identification of Labour Exploitation

Deceptive online job advertisements have emerged as a primary pathway into forced labour, yet systematic detection methods remain underdeveloped due to data scarcity and absence of empirically validated indicators. We formalise this detection challenge as a classification problem under signalling theory, where exploiters transmit costless signals mimicking legitimate communications across textual, visual, and structural dimensions. Using 464 verified cases (164 deceptive, 300 legitimate) collected through anti-slavery charities across nine origin countries and 21 industries, we develop multimodal detection models combining computer vision, natural language processing, and semantic embeddings. Through systematic feature ablation experiments and repeated stratified cross-validation, we demonstrate that individual modalities achieve substantial discriminatory power (ROC-AUC: 0.87--0.97), whilst their integration yields modest further gains. SHAP-based analysis reveals that text quality and domain-specific risk language are the primary discriminators, with readability indices, risk keyword density, and visa sponsorship mentions ranking highest, followed by visual colour and texture features. These production quality gaps reflect resource constraints that prevent exploiters from maintaining professional standards across all communication channels simultaneously. We operationalise findings through a proof-of-concept decision support system providing interpretable risk scores for practitioners. This work demonstrates how rigorous analytical frameworks can address complex humanitarian operations challenges characterised by information asymmetry and limited ground-truth data.

cs.CY↗

arXiv2026

Preference Analysis Using Random Spanning Trees: A Stochastic Sampling Approach to Inconsistent Pairwise Comparisons

Eliciting preferences from human judgements is inherently imprecise, yet most decision analysis methods force a single priority vector from pairwise comparisons, discarding the information embedded in inconsistencies. We instead leverage inconsistency to characterise preference uncertainty by examining all priority vectors consistent with the decision maker's judgements. Spanning tree analysis enumerates combinations of evaluation and weighting vectors from pairwise comparison subsets, each yielding a distinct preference vector and collectively defining a distribution over possible preference orderings. Since exponential growth renders complete enumeration prohibitive, we propose a stochastic random walk sampling approach with sample sizes formally established via statistical sampling theory. This enables two key metrics: Pairwise Winning Indices (PWIs), the probability one alternative is preferred to another, and Rank Acceptability Indices (RAIs), the probability an alternative attains a given rank. A notable advantage is applicability to incomplete pairwise comparisons, common in large-scale problems. We validate the methodology against complete enumeration on a didactic example, then demonstrate scalability on a telecommunications backbone infrastructure selection case study involving billions of spanning tree combinations. The approach yields probabilistic insights into preference robustness and ranking uncertainty, supporting informed decisions without the burden of exact enumeration.

econ.GN↗

arXiv2022

Shapley value-based approaches to explain the robustness of classifiers in machine learning

The use of algorithm-agnostic approaches is an emerging area of research for explaining the contribution of individual features towards the predicted outcome. Whilst there is a focus on explaining the prediction itself, a little has been done on explaining the robustness of these models, that is, how each feature contributes towards achieving that robustness. In this paper, we propose the use of Shapley values to explain the contribution of each feature towards the model's robustness, measured in terms of Receiver-operating Characteristics (ROC) curve and the Area under the ROC curve (AUC). With the help of an illustrative example, we demonstrate the proposed idea of explaining the ROC curve, and visualising the uncertainties in these curves. For imbalanced datasets, the use of Precision-Recall Curve (PRC) is considered more appropriate, therefore we also demonstrate how to explain the PRCs with the help of Shapley values. The explanation of robustness can help analysts in a number of ways, for example, it can help in feature selection by identifying the irrelevant features that can be removed to reduce the computational complexity. It can also help in identifying the features having critical contributions or negative contributions towards robustness.

cs.LG↗

arXiv2022

How fair were COVID-19 restriction decisions? A data-driven investigation of England using the dominance-based rough sets approach

During the COVID-19 pandemic, several countries have taken the approach of tiered restrictions which has remained a point of debate due to a lack of transparency. Using the dominance-based rough set approach, we identify patterns in the COVID-19 data pertaining to the UK government's tiered restrictions allocation system. These insights from the analysis are translated into "if-then" type rules, which can easily be interpreted by policy makers. The differences in the rules extracted from different geographical areas suggest inconsistencies in the allocations of tiers in these areas. We found that the differences delineated an overall north south divide in England, however, this divide was driven mostly by London. Based on our analysis, we demonstrate the usefulness of the dominance-based rough sets approach for investigating the fairness and explainabilty of decision making regarding COVID-19 restrictions. The proposed approach and analysis could provide a more transparent approach to localised public health restrictions, which can help ensure greater conformity to the public safety rules.

cs.CY↗

arXiv2018

Remaining Idle Time Aware Intelligent Channel Bonding Schemes for Cognitive Radio Sensor Networks

Channel Bonding (CB) is a technique used to provide larger bandwidth to users. It has been applied to various networks such as wireless local area networks (WLANs), Wireless Sensor Networks (WSNs), Cognitive Radio Networks (CRNs), and Cognitive Radio Sensor Networks (CRSNs). The implementation of CB in CRSNs needs special attention as Primary Radio (PR) nodes traffic must be protected from any harmful interference by Cognitive Radio (CR) nodes. On the other hand, CR nodes need to communicate without interruption to meet their data rate requirements. If CR nodes perform frequent channel switching due to PR traffic then it will be difficult to meet their quality of service (QoS) and data rate requirements. So, CR nodes need to select those channels which are stable. By stable, we mean those channels which cause less harmful interference to PR nodes and having less PR activity or long remaining idle time. In this paper, we propose our two approaches Remaining Idle Time aware intelligent Channel Bonding (RITCB) and Remaining Idle Time aware Intelligent Channel Bonding with Interference Prevention (RITCB-IP) for cognitive radio sensor networks which select those channels for CB which have longest remaining idle time. We compare our approaches with four schemes PRACB, SWA, KNOWS and AGILE. Simulation results show that our proposed approaches RITCB and RITCB-IP decrease harmful interference (HIR) and increases the life time of cognitive radio sensor nodes.

cs.NI↗