SMN Digest December 2024

1. Autoassess AI: Vision-Based Car Damage Assessment Using Deep Learning

Ma. Carmelle C. Pedrosa, Elmer Peramo, and Dr. Brenda Quismorio

This study addresses the need for an automated car damage assessment system to reduce processing time and increase throughput at the XYZ repair center, a facility currently reliant on manual, time-intensive evaluations. To meet this need, the researcher developed a modular AI-based solution leveraging computer vision and deep learning, specifically targeting damage location, type, and severity classification. The solution utilized EfficientNetV2B0 and MobileNetV2 models for location and severity classification, and YOLOv8 (You Only Look Once) for damage type detection. These models were trained and evaluated on a curated dataset of car damage images, meeting technical success criteria for accuracy, F1 score, and mean Average Precision (mAP). EfficientNetV2B0 achieved a 92% F1 score for location classification, while YOLOv8s achieved a 74.3% mAP in damage type detection. YOLOv8s performed well with visually distinct damages but faced challenges with subtle damage types, such as cracks. This AI-driven solution shows potential for improving operational efficiency, aligning with XYZ’s goal of streamlining damage assessments, enhancing customer experience, and setting a new standard in automotive repair services.

2. Adaptive Marketing: Redefining Personal Care Industry Tactics 

Wenzel Vaughn P. Pestaño and Ruth L. Legaspi

The COVID-19 pandemic disrupted consumer behavior and changed the market landscape across all industries – retail or business-to-business. This study specifically focuses on the personal care industry, which the pandemic has challenged to adapt its business model, marketing strategies, and action plans to retain the customers' evolving dispositions and behavior in the changing post-pandemic milieu. The primary objective was to identify actionable segments within the customer base and tailor marketing strategies to enhance engagement and retention.

Using historical data (2020-2023), the researchers applied data mining techniques and statistical analysis. K-means clustering segmented customers, while the Apriori algorithm identified upselling opportunities. Optimization techniques determined the best actions for each segment to improve revenue. The effectiveness of the strategy and action plans was evaluated by comparing control and treatment groups through conversion rates.

Key findings included a 0.71 silhouette score for clustering quality, 27% conversion rate for adaptive marketing strategies, 35.7% upselling frequency, a 7.91% increase in average order value (AOV), and a 25% reduction in monthly cancellation rates. This project highlighted the importance of updating customer segments and refining marketing strategies to boost engagement, retention, and business outcomes.

These insights provide a foundation for the company to strengthen its market position, increase customer loyalty, and drive sustained growth in the clustering quality, conversion rate, upselling frequency, average order value, and cancellation rates.

3. The Determinants of Turnover Intention of Accountants in Public Practice

Lila Andrea Vien Hernandez, Aisha Hannia Pangandaman, and Dr. Anna Maria E. Mendoza

Employee turnover continues to be a significant challenge, especially within accounting firms. In the Philippines, the professional services sector is among the top three industries with the highest turnover rates, which has raised concerns about workforce stability and retention. This study aims to investigate the factors influencing turnover intention among accountants in public practice in the Philippines. By analyzing the demographic profiles of accountants, the research examines how key determinants such as job satisfaction, affective commitment, continuance commitment, performance, role conflict, and role ambiguity contribute to turnover intention. Additionally, the study explores the moderating role of demographic characteristics in shaping these relationships.

A descriptive correlational research design was employed, involving 243 public accountants selected through simple random sampling. Data were collected through survey adapted from Shofiatul et al. (2016) and analyzed using multiple linear regression and moderation analysis with Jamovi software. 

The results underscore the importance of addressing affective commitment and role conflict to reduce turnover, while also emphasizing the need to consider demographic variables when formulating retention strategies. 

All articles published in SMN Digest are indexed in EBSCO Information Services and may be accessed in full text through Philippine E-Journals.