arXiv subjects

Ahmed Dawoud

Publications and source records attributed to Ahmed Dawoud.

5 recordsLinked to original sources

arXiv2026

Graph-Based Analysis of AI-Driven Labor Market Transitions: Evidence from 10,000 Egyptian Jobs and Policy Implications

How many workers displaced by automation can realistically transition to safer jobs? We answer this using a validated knowledge graph of 9,978 Egyptian job postings, 19,766 skill activities, and 84,346 job-skill relationships (0.74% error rate). While 20.9% of jobs face high automation risk, we find that only 24.4% of at-risk workers have viable transition pathways--defined by $\geq$3 shared skills and $\geq$50% skill transfer. The remaining 75.6% face a structural mobility barrier requiring comprehensive reskilling, not incremental upskilling. Among 4,534 feasible transitions, process-oriented skills emerge as the highest-leverage intervention, appearing in 15.6% of pathways. These findings challenge optimistic narratives of seamless workforce adaptation and demonstrate that emerging economies require active pathway creation, not passive skill matching.

cs.CY↗

arXiv2026

Reading Between the Lines: Deconfounding Causal Estimates using Text Embeddings and Deep Learning

Estimating causal treatment effects in observational settings is frequently compromised by selection bias arising from unobserved confounders. While traditional econometric methods struggle when these confounders are orthogonal to structured covariates, high-dimensional unstructured text often contains rich proxies for these latent variables. This study proposes a Neural Network-Enhanced Double Machine Learning (DML) framework designed to leverage text embeddings for causal identification. Using a rigorous synthetic benchmark, we demonstrate that unstructured text embeddings capture critical confounding information that is absent from structured tabular data. However, we show that standard tree-based DML estimators retain substantial bias (+24%) due to their inability to model the continuous topology of embedding manifolds. In contrast, our deep learning approach reduces bias to -0.86% with optimized architectures, effectively recovering the ground-truth causal parameter. These findings suggest that deep learning architectures are essential for satisfying the unconfoundedness assumption when conditioning on high-dimensional natural language data

cs.AI↗

arXiv2026

Signal in the Noise: Decoding the Reality of Airline Service Quality with Large Language Models

Traditional service quality metrics often fail to capture the nuanced drivers of passenger satisfaction hidden within unstructured online feedback. This study validates a Large Language Model (LLM) framework designed to extract granular insights from such data. Analyzing over 16,000 TripAdvisor reviews for EgyptAir and Emirates (2016-2025), the study utilizes a multi-stage pipeline to categorize 36 specific service issues. The analysis uncovers a stark "operational perception disconnect" for EgyptAir: despite reported operational improvements, passenger satisfaction plummeted post-2022 (ratings < 2.0). Our approach identified specific drivers missed by conventional metrics-notably poor communication during disruptions and staff conduct-and pinpointed critical sentiment erosion in key tourism markets. These findings confirm the framework's efficacy as a powerful diagnostic tool, surpassing traditional surveys by transforming unstructured passenger voices into actionable strategic intelligence for the airline and tourism sectors.

cs.IR↗

arXiv2025

ProRCA: A Causal Python Package for Actionable Root Cause Analysis in Real-world Business Scenarios

Root Cause Analysis (RCA) is becoming ever more critical as modern systems grow in complexity, volume of data, and interdependencies. While traditional RCA methods frequently rely on correlation-based or rule-based techniques, these approaches can prove inadequate in highly dynamic, multi-layered environments. In this paper, we present a pathway-tracing package built on the DoWhy causal inference library. Our method integrates conditional anomaly scoring, noise-based attribution, and depth-first path exploration to reveal multi-hop causal chains. By systematically tracing entire causal pathways from an observed anomaly back to the initial triggers, our approach provides a comprehensive, end-to-end RCA solution. Experimental evaluations with synthetic anomaly injections demonstrate the package's ability to accurately isolate triggers and rank root causes by their overall significance.

cs.AI↗

arXiv2022

A Novel Enhanced Convolution Neural Network with Extreme Learning Machine: Facial Emotional Recognition in Psychology Practices

Facial emotional recognition is one of the essential tools used by recognition psychology to diagnose patients. Face and facial emotional recognition are areas where machine learning is excelling. Facial Emotion Recognition in an unconstrained environment is an open challenge for digital image processing due to different environments, such as lighting conditions, pose variation, yaw motion, and occlusions. Deep learning approaches have shown significant improvements in image recognition. However, accuracy and time still need improvements. This research aims to improve facial emotion recognition accuracy during the training session and reduce processing time using a modified Convolution Neural Network Enhanced with Extreme Learning Machine (CNNEELM). The system entails (CNNEELM) improving the accuracy in image registration during the training session. Furthermore, the system recognizes six facial emotions happy, sad, disgust, fear, surprise, and neutral with the proposed CNNEELM model. The study shows that the overall facial emotion recognition accuracy is improved by 2% than the state of art solutions with a modified Stochastic Gradient Descent (SGD) technique. With the Extreme Learning Machine (ELM) classifier, the processing time is brought down to 65ms from 113ms, which can smoothly classify each frame from a video clip at 20fps. With the pre-trained InceptionV3 model, the proposed CNNEELM model is trained with JAFFE, CK+, and FER2013 expression datasets. The simulation results show significant improvements in accuracy and processing time, making the model suitable for the video analysis process. Besides, the study solves the issue of the large processing time required to process the facial images.

cs.CV↗