Ioana Petrea

Ms. Ioana Petrea


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 November 2025 in Electronics
Verified
Journal Article
Open access
PDF file
Marian Pompiliu I CristescuMarian Pompiliu I Cristescu
Marian Pompiliu I Cristescu
CBClaudiu Brandas
Claudiu Brandas
Dumitru Alexandru MaraDumitru Alexandru Mara
Dumitru Alexandru Mara
IPIoana Petrea
Ioana Petrea
The increasing use of complex “black-box” models for financial news sentiment analysis presents a challenge in high-stakes settings where transparency and trust are paramount. This study introduces and validates a finance-focused, fully reproducible, open-source workflow for building, explaining, and evaluating sector-specific sentiment models mapped to standard market taxonomies and investable proxies. We benchmark interpretable and transformer-based models on public datasets and a newly constructed, manually annotated gold-standard corpus of 1500 U.S. sector-tagged financial headlines. While a zero-shot FinBERT establishes a reasonable baseline (macro F1 = 0.555), fine-tuning on our gold data yields a robust macro F1 = 0.707, a substantial uplift. We extend explainability to the fine-tuned FinBERT with Integrated Gradients (IG) and LIME and perform a quantitative faithfulness audit via deletion curves and AOPC; LIME is most faithful (AOPC = 0.365). We also quantify the risks of weak supervision: accuracy drops (−21.0%) and explanations diverge (SHAP rank ρ = 0.11) relative to gold-label training. Crucially, econometric tests show the sentiment signal is reactive, not predictive, of next-day returns; yet it still supports profitable sector strategies (e.g., Technology long-short Sharpe 1.88). Novelty lies in a finance-aligned, sector-aware, trustworthiness blueprint that pairs fine-tuned FinBERT with audited explanations and uncertainty checks, all end-to-end reproducible and tied to investable sector ETFs.

3 October 2026 in Mathematics
Verified
Journal Article
Open access
PDF file
Marian Pompiliu I CristescuMarian Pompiliu I Cristescu
Marian Pompiliu I Cristescu
IPIoana Petrea
Ioana Petrea
Sparse time-indexed transaction data create a statistical-learning problem in which low basket occupancy, combinatorial candidate growth, temporal heterogeneity, and data-quality sensitivity complicate interpretable pattern discovery. Using a multi-year single-case dataset from an independently operated SME restaurant point-of-sale (POS) system, this study proposes a reproducible, sparsity-aware framework that separates global distributional characterization, unsupervised co-occurrence learning, statistical qualification, adjusted outcome modeling, and transparent prioritization. The empirical application comprises 31,157 baskets, 139,396 valid item lines, 710 products, and 762 active days; the 31,157 × 710 basket-product representation has 0.630% density. Multiplicity-screened association-rule learning retains 1174 directional rules. In a strictly subsequent validation period, 93.6% of discovery rules preserve lift above one, 49.3% satisfy all prespecified thresholds again, and rank correlations for support, confidence, and lift range from 0.803 to 0.849. An estimated-dispersion NB2 model with day-clustered uncertainty preserves the principal basket-breadth associations, while Gamma sensitivity analysis confirms the direction, but not invariant magnitude, of late-service basket-value effects. The methodological contribution is not a new stand-alone algorithm, but an auditable evidence architecture that explicitly separates candidate discovery, multiplicity screening, effect assessment, temporal replication, adjusted modeling, and human-supervised prioritization. Because the empirical evaluation is based on a single time-indexed case, the reported effect magnitudes remain case-specific.

21 July 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Marian Pompiliu I CristescuMarian Pompiliu I Cristescu
Marian Pompiliu I Cristescu
CBClaudiu Brandas
Claudiu Brandas
Dumitru Alexandru MaraDumitru Alexandru Mara
Dumitru Alexandru Mara
IPIoana Petrea
Ioana Petrea
We introduce Explainable AI for Financial-News Sentiment Mining, a complete research workflow that anyone can reproduce at no cost. The workflow relies only on the free-tier of the Marketaux news-aggregation application programming interface (API) and widely available Python libraries. Our objective is to retrieve every United States technology-sector news article (tagged in the industries Technology and Semiconductors) published between January and June 2025, save each day’s material in a clear Excel format, and measure sentiment with methods that remain understandable to human readers. The sentiment layer combines two transparent techniques. First, we use VADER (Valence Aware Dictionary for Sentiment Reasoning), a rule-based lexicon that assigns a polarity score to each word, allowing us to highlight positive and negative tokens directly in the headline text. Second, we train a simple term-frequency–inverse-document-frequency model (TF–IDF) with logistic regression and explain its decisions through SHAP (Shapley Additive Explanations) feature-importance plots. This dual approach shows both the individual words that drive sentiment and the broader patterns that a supervised model discovers. We expect the result to be a practical, transparent toolset that helps researchers and practitioners explore news sentiment.