Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal JEECS (Journal of Electrical Engineering and Computer Sciences) Journal of Technology Informatics and Engineering
Lu, Yifei
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
A Constrained, Data-Driven Budgeting Framework Integrating Macro Demand Forecasting and Marketing Response Modeling Lu, Yifei; Zhou, Hailin; Zhang, Yitian
Journal of Technology Informatics and Engineering Vol. 4 No. 3 (2025): DECEMBER | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v4i3.466

Abstract

Budgeting and financial planning & analysis (FP&A) increasingly require combining macroeconomic signals, channel-level marketing effectiveness, and hard accounting constraints into a single, auditable decision process. This paper proposes and empirically evaluates an end-to-end framework that (i) forecasts category-level demand from public macro data, (ii) learns diminishing-returns marketing response curves, and (iii) solves a constrained portfolio optimization problem to allocate marketing spend while satisfying SG&A and cash-flow guardrails consistent with real public-company statements. Using quarterly Personal Consumption Expenditures (PCE) components from FRED (durable goods, nondurable goods, and services) as a proxy for market demand, we compare seasonal naïve, SARIMAX, gradient boosting, and a multivariate VAR model in a rolling backtest (2018Q1-2025Q3). In parallel, we estimate marketing response from the Advertising dataset (TV, radio, and newspaper spend) via linear models, gradient boosting, and a Hill-function saturation model. We then calibrate financial constraints-gross margin, SG&A ratio, and operating cash-flow coverage-directly from Apple Inc.’s FY2025 Form 10-K filed with the SEC, and integrate all components into a Monte Carlo-evaluated budgeting optimizer. Results show that multivariate models improve total-demand accuracy (≈2.85% MAPE) and that nonlinear response curves indicate strong diminishing returns and negligible incremental value for newspaper spend. The constrained optimizer produces stable allocations that trade off expected operating profit and downside risk, and it highlights a practical insight: budgets that exactly meet a ratio-based cap under point forecasts may violate constraints under realistic demand uncertainty. The proposed workflow is fully reproducible from public data sources and provides a template for transparent, constraint-aware budgeting.
Review-Grounded Explainable Recommendation with Faithfulness Evaluation on Amazon Reviews Chang, Xiaohan; Lu, Yifei; Zhong, Ziliang Samuel
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 11 No. 1 (2026): JEECS (Journal of Electrical Engineering and Computer Sciences) - In press
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v11i1.2

Abstract

Review text can support explainable recommendations, but many recommender systems still optimize ranking accuracy without providing verifiable textual evidence, or they attach post-hoc explanations whose faithfulness to the model is unclear. This study addresses the lack of a reproducible evaluation setting that jointly measures recommendation quality and whether extracted review evidence actually supports model scoring. We propose Review-Grounded eXplainable Recommender (RGXRec), a lightweight hybrid method that combines interaction signals and TF-IDF review similarity, and we evaluate it on the Luxury Beauty and Video Games subsets of the Amazon Review Data. The pipeline includes rating thresholding, iterative 5-core pruning, chronological leave-one-out splitting, ranked recommendation, extractive evidence generation, and faithfulness evaluation. We compare RGXRec with popularity, metadata-graph KNN, SVD-MF, and ReviewSim using NDCG@K, Recall@K, MRR, evidence coverage, ROUGE-1, sentiment agreement, and a term-attribution faithfulness score. On Luxury Beauty, RGXRec achieves the best ranking performance, reaching NDCG@10 of 0.3606 and outperforming the strongest single-view baseline. On Video Games, collaborative and metadata signals remain stronger for ranking, but RGXRec preserves competitive accuracy while providing non-zero review-grounded faithfulness that interaction-only baselines cannot offer. These findings show that review-grounded recommendation should be evaluated on both ranking quality and explanation faithfulness.
Co-Authors Chang, Xiaohan Zhang, Yitian Zhong, Ziliang Samuel Zhou, Hailin