AIForA Lab · 박대근 교수 연구실

Forecast the future with data. Support decisions with AI.

A generative-AI research lab whose work spans social sciences (business & economics), life sciences, rehabilitation (sports, psychology & art therapy), nursing, pharmacy & medicine, and engineering — we study generative AI that applies to every field, and turn research into deployable tools. Led by Prof. Dae Keun Park (박대근) · 차의과학대학교 일반대학원 AI헬스케어융합학과 · AIForA Lab.

박대근 교수 연구실 AIForA Lab(AI Forecasting Analytics Lab) · 차의과학대학교 일반대학원 AI헬스케어융합학과

25+Publications
6Research areas
37Deployed AI portals
12Advised students
16AI-integrated courses
Watch

Lab Introduction

A short overview of the lab.

Research

Research Areas

Eight threads spanning prediction, causal inference, decision support, and AI-augmented education.

Text & Media Big-Data Analytics

Semantic-network analysis, topic modeling, churnalism, and crisis communication over large news corpora.

Bio-Healthcare Machine Learning

Multi-task and interpretable models for pharmacokinetics (drug clearance, volume of distribution) and multi-outcome clinical risk prediction.

Generative-AI Applications

Embedding-based ESG analysis and trust-by-design RAG avatar chatbots that turn LLMs onto domain problems.

Pension & Policy Microsimulation

Microsimulation and Monte-Carlo models for the Basic Pension, National Pension unfunded liability, and welfare/tax policy.

Corporate Finance, Accounting & ESG

How dividends, executive stock-linked pay, debt maturity, bond ratings, and ESG / tax-evasion news move firm value.

Financial & Economic Forecasting

Unit-root and level-change testing, long-horizon mean reversion, and structural-change detection to model and forecast markets and macro series.

AI in Education & Advising

Generative-AI teaching bots, major and career advising agents, curriculum redesign, and hands-on “build-your-own-AI” courses that grow AI literacy.

Business & Data Analytics

Statistical learning and big-data analytics — from business statistics to financial and managerial big-data modeling — that underpin the applied work.

Publications

Selected Publications

Grouped by research area. Click any paper to expand its topic, methodology, and results — each lists its published journal.

Text & Media Big-Data Analytics8

AI-Data-Based Art-Therapy Convergence MajorJ. of Learner-Centered Curriculum & Instruction, 20(19), 2020
TopicDesigning a convergence major that fuses art therapy with AI and data skills for the 4th industrial revolution.
MethodologySurveyed 113 art-therapy students with frequency and regression analysis, plus morphological keyword analysis of open-ended responses.
ResultsStudents saw AI-data convergence as a key opportunity; prior awareness and AI-data knowledge shaped major choice, yielding a proposed six-semester curriculum.
Have the Elderly Really Changed? The 'Active Senior'Korean J. of Communication Studies, 24(2), 2025
TopicWhether an economically- and digitally-capable 'active senior' cohort is emerging in Korea.
MethodologyMerged 10 years (2014–2023) of Financial-Panel and media-audience data across six age groups for time-series comparison.
ResultsThe 55–74 groups narrowed leisure/telecom-spend and portal/TV-news gaps versus 45–54 while wealth-income gaps widened — evidence of active seniors.
Older Adults' Political Orientation in the Digital-Transformation EraKorean J. of Journalism & Communication Studies, 69(2), 2025
TopicThe interplay of digital literacy, online participation, and political orientation among older adults.
Methodology2020–2023 Korea Media Panel and Press-Foundation data analyzed with statistical matching.
ResultsOlder adults (especially 55–64) improved digital competencies and narrowed the gap with younger cohorts, with associated shifts in engagement and political preference.
China-Market Distribution & Tourism Strategy via Big-DataKorea Logistics Review, 27(2), 2017
TopicStrategy to attract Chinese tourists to Korea's distribution and tourism sectors.
MethodologyText-network (semantic) analysis of 2015 news containing 'China' and 'tourism', extracting centrality and topic clusters.
ResultsMarketing centered on duty-free/hospitality (Seoul-biased) while destination and cultural value were under-leveraged — recommends stronger linkage, regional diversification, and active Hallyu use.
Positive/Negative Milk-Consumption News Topics via Generative AIHealth Communication Research, 23(2), 2024
TopicMapping positive and negative issues around milk consumption in the news.
MethodologyGenerative-AI semantic-network and topic modeling over 1,338 milk-related articles across five years.
ResultsPositive topics (health, safety, sustainable/subscription consumption, protein products, logistics) and negative ones (declining consumption, plant-based substitutes, price rises, low birthrate, COVID) — insight for dairy policy.
Semantic-Network Analysis of Community-Sports News in Aged RegionsJ. of Korea Society for Wellness, 2026
TopicCommunity-sports news topics across ten aging and super-aged cities in northern Gyeonggi Province.
MethodologySemantic-network analysis of community-sports news coverage.
ResultsSurfaces latent resident policy demands beyond the usual supplier-centric view, supporting region- and lifecycle-tailored community-sports policy.
Role of K-Culture for the Vietnam Market after COVID-19J. of Product Research, 39(6), 2021
TopicLeveraging Hallyu (K-culture) to appeal to the Vietnamese market after COVID-19.
MethodologyMorphological and text-network analysis of five years of 'Vietnam tourist' news.
ResultsKorea–Vietnam is strongly linked via football/sports, but the Hallyu–product/retail linkage is weak — recommends Hallyu-linked hit products and systematic promotion.
Organizational Communication in Early COVID-19: 34 UniversitiesJ. of Practical Advertising & PR, 16(3), 2023
TopicCrisis-response communication of organizations in the early COVID-19 period.
MethodologySMCRE-model analysis of 1,761 messages from 34 Korean universities over six months.
ResultsMetro-area and large universities communicated crisis response and stakeholder safety more promptly, via president-level sources and dedicated COVID channels.

Bio-Healthcare Machine Learning2

Multi-Task Gradient Boosting with Multi-Modal Molecular RepresentationsPLOS One, 21(4), 2026
TopicPredicting two pharmacokinetic parameters — drug clearance and volume of distribution — simultaneously.
MethodologyMulti-task gradient boosting over multi-modal molecular representations.
ResultsAccurate, scalable, and interpretable simultaneous PK prediction directly from chemical structure.
Multicenter Validation of a Scalable, Interpretable, Multitask Clinical Prediction Modelnpj Digital Medicine (Nature), 8:583, 2025
TopicPredicting multiple post-operative complications together rather than one at a time.
MethodologyTree-based multitask learning on 16 routine preoperative EHR features, externally validated across cohorts.
ResultsAUROCs ~0.81 (AKI), ~0.89–0.93 (respiratory failure), ~0.85–0.91 (mortality), with interpretable per-variable contributions.

Generative-AI Applications2

Domestic Applicability of SASB ESG Issues via Generative-AI EmbeddingJ. of the Korean OR/MS Society, 50(3), 2025
TopicWhether SASB's industry-specific ESG issues fit Korean industries, using healthcare as the case.
MethodologyGenerative-AI sentence embeddings to classify corporate healthcare news and surface recurrent issues.
ResultsNews-based ESG salience aligns significantly with SASB (p<0.05), yet some domestically distinct issues reveal industry- and region-specific peculiarity.
Trust-by-Design of an Avatar Chatbot for Major/Career AdvisingJ. of Digital Contents Society, 26(12), 2026
TopicIntegrating multi-layered trust signals into a multimodal RAG avatar chatbot for major and career advising.
MethodologyDerived trust signals across identity, response quality, interaction naturalness, and operational-policy transparency, then measured user perception.
ResultsPolicy-transparency signals were perceived most strongly while affective response quality lagged the cognitive side, pinpointing where trust design breaks down.

Pension & Policy Microsimulation4

Empirical Analysis on the Elasticity of Tax Revenue in KoreaKorean Economic Forum (formerly Yonsei Economic Studies), 22(1), 2015
TopicEstimating the elasticity of national tax revenue with respect to its economic base.
MethodologyEmpirical elasticity analysis of Korean tax-revenue and macroeconomic data.
ResultsQuantifies how responsive tax revenue is to the base, informing revenue forecasting and fiscal-policy design.
Effects of Basic-Pension Changes on Income Distribution and PovertyKorean Association of Public Finance, 2018 Autumn Conference Proceedings
TopicDistributional and poverty effects of Korea's Basic Pension reforms.
MethodologyMicrosimulation on the 10th Financial-Panel, comparing no-pension, current, and reformed scenarios.
ResultsThe Basic Pension improved income distribution (Gini, quintile ratio) and reduced poverty; benefit-level hikes helped only modestly.
Crowding-Out of Livelihood Benefits on the Basic Pension's EffectJ. of Fiscal Policy, 23(4), 2021
TopicWhether livelihood-benefit crowd-out weakens the Basic Pension's redistribution and poverty relief.
MethodologyMicrosimulation on the 13th Financial-Panel.
ResultsThe Basic Pension substantially improves redistribution and reduces poverty; recent reforms and the crowd-out effect are small because few households receive both benefits.
Probabilistic Estimation of the National Pension's Unfunded LiabilityJ. of Pension Studies, 15(1), 2025
TopicQuantifying the uncertainty in the National Pension's unfunded liability.
MethodologyMonte-Carlo simulation over policy scenarios (replacement and contribution rates) and environment scenarios (wage growth, benefit growth, discount rate).
ResultsProduces a full probability distribution instead of a single point estimate — a risk-based tool for pension-reform design.

Corporate Finance, Accounting & ESG5

Effects of Temporary Earnings on Dividends in KoreaApplied Economics Letters (Taylor & Francis), 29(21), 2044–2046, 2022
TopicHow temporary (transitory) earnings affect corporate dividend policy in Korea.
MethodologyAnalyzed cash-dividend data of Korean firms from 2001 to 2017, split by debt type.
ResultsPrivate-debt-only firms raise dividends with temporary earnings (dampened by investment opportunities); public-debt firms do not — supporting precautionary-savings and signaling hypotheses.
Effects of Incentive Alignment on Debt Maturity StructureJ. of Insurance and Finance, 23(3), 2012
TopicWhether executive stock-linked pay (incentive alignment) shapes corporate debt maturity.
MethodologyAnalyzed interactions of managerial ownership with liquidity risk and investment opportunities.
ResultsOwnership shortens maturity when liquidity risk is low but lengthens it when high; high-growth firms prefer short-term debt — consistent with the under-investment hypothesis.
Negative ESG News and Firm ValueKorean J. of Broadcasting & Telecommunication Studies, 38(4), 2024
TopicThe effect of negative ESG news coverage on firm value (market-to-book ratio).
MethodologyWeb-scraping plus the ChatGPT-4.0 API to classify 30,098 negative ESG articles for 1,845 listed firms (2019–2022); panel regression.
ResultsNegative ESG news significantly lowers MTB, driven mainly by Governance issues, and strongest in healthcare/pharma, chemicals, and finance.
Tax-Evasion Controversy and Firm Value via Big-DataJ. of Internet Computing and Services, 22(6), 2021
TopicWhether tax-evasion controversy in portal news erodes firm value.
MethodologyCrawled portal news to build per-firm keyword-frequency time series; panel regression and impulse-response analysis.
ResultsHigher controversy frequency lowers firm value, with the effect decaying gradually over about 12 months.
Determinants of Corporate-Bond Rating DisagreementJ. of Korean Economic Studies, 33(2), 2015
TopicWhy credit-rating agencies disagree on the same corporate bond.
MethodologyEmpirical analysis relating split ratings to issuer financial characteristics and information asymmetry.
ResultsIdentifies the factors that drive rating disagreement, with implications for bond pricing and rating quality.

Financial & Economic Forecasting4

A Simultaneous Test of Unit Root and Level ChangeJournal of Forecasting (Wiley), 29, 301–312, 2010
TopicDistinguishing whether a time series has a unit root, a level change, or both — usually tested separately.
MethodologyDerived a likelihood-ratio test from a state-space model, with null distributions built by simulation.
ResultsThe joint test identifies the true underlying structure; validated on simulations and two Korean macroeconomic series.
Distribution-Based Level Change Detection in a Random-Level Forecasting ModelJ. of the Korean Institute of Industrial Engineers, 43(4), 2017
TopicUnexpected level changes cause persistent forecasting errors in macro and financial series.
MethodologyDerived the correct statistical distribution of the level-change statistic and adapted the forecasting equation accordingly.
ResultsImproved change detection and forecast accuracy, validated on simulations and two empirical cases.
Long-Term Mean Reversion of Stock Prices Based on Fractional IntegrationInternational Journal of Management Science, 17(2), 2011
TopicThe very-long-horizon behavior of stock returns versus random-walk models.
MethodologyIntroduced a fractionally integrated process into the nonstationary component of a stock-price model and tested NYSE returns.
ResultsNegative autocorrelations persist up to ~10 years, implying market inefficiency can last far longer than random-walk models predict.
Pairs-Trading Algorithm with Structural-Change DetectionJ. of the Korean OR/MS Society, 42(3), 2017
TopicImproving pairs-trading performance by handling structural breaks in cointegration.
MethodologyEmbedded a structural-change detection procedure (cointegration breaks, unit-root tests) into the algorithm, tested by simulation and empirics.
ResultsOutperforms the baseline on risk-adjusted return, with a steady upward cumulative P/L at low variance.
Projects

Deployed Research Portals

Beyond papers — portals, bots, and dashboards people can actually use.

Text & Media Big-Data Analytics
Lab Toolkit · News Meta-Analysis Portal

Lab Toolkit · News Meta-Analysis Portal →

Members-only program portal — the news meta-analysis pipeline (crawl → filter → morphology → embedding → topic) with install commands, docs, and release notes.

Portal-News Churnalism Analysis

Portal-News Churnalism Analysis →

Measuring cross-outlet news-story synchronization and duplication across Korean news portals.

Schizophrenia-News Framing Study — Portal

Schizophrenia-News Framing Study — Portal →

Five-year (2021–2026) analysis of episodic/thematic framing, stigma tone, and cross-outlet churnalism in schizophrenia news — an illustrated storybook, analysis report, meeting materials, a Q&A bot, and a human-coder validation tool.

Korean Management Science · 50 Years — Retrospective & Vision

한국 경영과학 50년 · 회고와 전망 →

한국경영과학회 창립 50주년 기념 『경영과학』 특별섹션을 위한 회고·전망 리뷰 — KCI에 수록된 학술지 초록 코퍼스를 시맨틱 네트워크 분석·토픽모델링으로 매핑하고, 생성형 AI로 주요 성과·세부분야 진화·미래 연구의제를 종합.

Pocheon News AI Newsroom

Pocheon News — AI Newsroom →

A local AI newsroom that rewrites hard news to be easy to read, with trust built into the system.

The Scope of Immersive Media

The Scope of Immersive Media · 30-Year Research Tree →

A scoping review and bibliometric study of 52,351 SCIE/SSCI-level articles (1995–2025) — research portal with the study, the English manuscript (co-authors only), protocol and PRISMA-ScR, figures, data and a 3D explorer

Bio-Healthcare AI
Surgery Names to International Procedure Codes

Surgery Names to International Procedure Codes →

Hospitals write surgery names freely — 105,979 distinct spellings across 280,356 records — while the world reports in seven-character ICD-10-PCS codes. Their vocabularies overlap by only 7.1%, so string matching fails. A picture-book portal explaining the semantic-similarity approach, the two datasets, and exactly where the project stands.

AbSwitch · Antibody IV→SC Formulation AI

AbSwitch · Antibody IV→SC Formulation AI →

AI system converting monoclonal antibodies from intravenous (IV) to subcutaneous (SC) delivery — a mechanism knowledge graph (mAb-GATED) and multimodal fusion prediction (AbFuseNet) forecast formulation stability and re-engineer optimal excipient combinations. Includes an interactive pipeline, a PK database dashboard, a formulation-stability primer, and a live avatar presenter.

Tacrolimus Research Portal

Tacrolimus Research Portal →

Pharmacokinetics research portal for the immunosuppressant tacrolimus.

Calcium Safety · Food vs Supplement AI Meta-Synthesis

칼슘 섭취 안전성 · 식품 vs 보조제 AI 메타종합 →

고함량 칼슘 보조제의 부작용(심근경색·신장결석 등)과 식품 섭취의 안전성을 흡수 동역학(‘동역학 과잉’ 가설) 관점에서 규명하는 AI 다중에이전트 증거 종합 — 가설 도출 과정·기전 인과그래프 분석·차별화된 생성형 AI 방법론·검증된 근거 요약 포함 · 생명과학대학 바이오식의약학 전공·일반대학원 생명과학과 주관, 일반대학원 AI헬스케어융합학과·AIForA Lab 지원

DarThera · Digital Art-Therapy Meta-Analysis

DarThera · 디지털 미술치료 메타분석 →

A generative-AI + human meta-analysis methodology for digital art therapy — a 6-step Colab pipeline (collect → filter → PICOS → extract → analyze → interpret), plus manuscript, tutorial, and an AI data-extraction guide.

SilverCare · AI Elder-Care Evidence Portal

SilverCare · AI Elder-Care Evidence Portal →

Does AI care technology actually improve older adults’ health and quality of life? A causal knowledge graph built from the literature, GATED link prediction for untested hypotheses, and a claim-versus-evidence gap analysis against news discourse.

Dementia-Prevention Cognitive Health Portal

Dementia-Prevention Cognitive Health Portal →

An AI platform linking cognitive self-checks with evidence-based training games and open research.

Blood-Pressure Analysis Storybook

Blood-Pressure Analysis Storybook →

An illustrated book on blood-pressure interpolation, estimation, and prediction — from data to models.

Generative-AI Research & Creative Work
AI Avatar Dance

AI Avatar Dance →

A 3D anime avatar that mirrors your face, hands, and full body through the webcam — and dances along to choreography videos on a lit stage.

LLM Jury Research

LLM Jury Research — Three Questions →

Why do LLM juries help only on hard tasks? Prior work, five gaps, three hypotheses, and a within-subject agent-simulation design — explained with picture-book visuals.

LLM Jury Simulation Results

LLM Jury — Simulation Results →

900 constructed pairs, 7 judges, 25,200 judgments. A 2x2 within-subject test of rubric and anchor effects — with the analysis notebook and raw CSV files open for download.

Scripture × LLM

Scripture × LLM — Do LLMs Read the Bible Differently by Country? →

Six Korean, US and Chinese LLMs × English, Korean and Chinese × passages on state authority (Romans 13, Acts 5:29). Background, hypotheses, methods and workplan are public; results are members-only.

Regaining Trust in AI — research card

AI와 인간 조언자의 신뢰 회복 →

AI 조언자가 예측을 틀린 뒤 신뢰는 얼마나 빨리 돌아오는가 — 그리고 그 충격이 일회성 이상치였는지 영구적 수준변화였는지가 회복 속도를 가르는가. Weight of Advice로 측정한 2×2 예측 실험과, 참가자가 실제로 본 충격의 구조에 관한 디스커션. 가설·방법론·현재 결과·재현 가능한 R 그림·심사자 대응 전략 수록.

MindPrint · AI That Writes Like You

MindPrint · 나처럼 글 쓰는 AI →

A portal for the Mindprint-Driven Recommendation study — a kids’ storybook, manuscript version comparisons, experiment code, results, and human evaluation in one place.

ContextAmp AI · Research & Patent Portal

ContextAmp AI · Research & Patent Portal →

AIForA Lab · Department of AI Healthcare Convergence · General Graduate School of CHA University. Front-end generative AI, a P25-0418-based adaptive audio core, and back-end generative AI — with a working microphone prototype.

PinkPop — AI Girl-Group MV & Avatar Portal

PinkPop (핑크팝) — AI 3인조 걸그룹 뮤직비디오 & 아바타 포털 →

Google Veo 3.1 AI 뮤직비디오 ('Midnight in Manhattan'), 3인조 아바타 캐릭터 시트(로하·미르·나린) 및 10곡 수록 앨범 통합 포털.

8 Seconds Later — AI Tech Drama

8 Seconds Later — AI Tech Drama →

Teaser and concept site for a 12-episode AI tech drama.

Economics, Finance & Policy Research
Real Value-Added Forecasting — Research Program

Real Value-Added Forecasting — Research Program →

Industry real value-added forecasting, from AR/VAR/BVAR foundations to scenario projections. Two papers — 36-industry quarterly and 70-industry monthly (mixed-frequency SSM) — with a reproducible, chapter-by-chapter walkthrough.

Structural Change Lab

Structural Change Lab · Models & Algorithms →

A password-protected research portal that reconstructs the source material in clear Korean and implements its structural-change models and algorithms as a Google Colab-ready Python notebook. Includes the original-reference PDF, methodology guide, and downloadable code.

Hanwoo Market AI Portal

Hanwoo Market AI Portal →

Korean-beef market forecasting and an AI newsroom — market-analysis chat, P10/P50/P90 price forecast, a public-data dashboard, and a 5-model LLM news studio.

SRT Securitization Study

SRT Securitization Study →

Significant Risk Transfer (SRT) securitization and bank capital-relief — empirical study + explainer.

Liquor Tax Research & Storybook

Liquor Tax Research & Storybook →

Ad-valorem vs. specific liquor taxation and price elasticity, told through illustrated storybooks and a research plan.

GreenCart — Low-Carbon Shopping

GreenCart — Low-Carbon Shopping →

A low-carbon livestock shopping concept for a greener planet.

AI Teaching & Course Portals
CHA Love Letter AI · Student Newsroom

CHA Love Letter AI · Student Newsroom →

Students pick an open-access paper from 41 Nature research journals, AI drafts the story, five AI jurors from different vendors check it line by line against the source, and a student reporter signs off.

Pocheon News · Local Interpretive Journalism

Pocheon News · Local Interpretive Journalism →

Reporters search the web for what is happening in Pocheon, read it closely, and write interpretive stories. 40 beats, one per reporter.

CHA Campus News · Student Newsroom

CHA Campus News · Student Newsroom →

Academic affairs, admissions, research, student life, careers and facilities — 41 beats covered by student reporters.

Green Cart News · Climate and Everyday Life

Green Cart News · Climate and Everyday Life →

Where buying, using and throwing away meets the planet — climate, energy, food, waste and nature across 42 beats.

Management in the Age of Advanced AI

AI 고도화 시대의 경영 →

차의과학대학교 헬스케어융합대학 경영학전공의 미래설계 Ⅱ 오리엔테이션 포털로, 경영학 전공에 관심 있는 1학년 학생을 위한 전공입문 프로그램이다. 매출은 역대 최고인데 통장은 비어 있는 재활 필라테스 스튜디오 한 곳의 사례를 8부작 드라마로 따라가며, 회계·재무·마케팅·인사조직·전략 다섯 렌즈를 30분 만에 관통한다. 15주 일정표와 강의계획서 전문을 함께 두었고, 과목의 모든 내용을 아는 gpt-5-mini 질의응답 창구에서 수업 운영과 진로를 직접 물어볼 수 있다.

AI Case Coaches for the Business Case Contest

경영사례개발대회 인공지능 사례 코치 →

2026 경영사례개발대회에 참가하는 헬스케어경영, 스포츠경영, 미디어경영, 심리경영, 바이오경영, 데이터경영, 글로벌비즈니스AI의 일곱 그룹을 위해 과제마다 따로 만든 인공지능 사례 코치 모음이다. 각 코치는 비대면진료 제도화, 의료광고 규제, 가명정보 활용, 첨단재생바이오법, 외국인환자 유치 실적처럼 과제에 필요한 공식 통계와 법령을 출처와 기준 시점과 함께 안내한다. 답변은 문제의 정의와 사업 모델의 설계와 실행 계획이라는 경영사례의 세 질문을 따르며, 팀 아이디어를 붙여 넣으면 보완할 점과 이번 주에 할 다음 행동을 돌려준다. 한국어와 영어로 대화하고 말로 묻고 음성으로 들을 수 있으며, 지도 교수가 어느 언어로 지식을 추가하더라도 자동 번역되어 두 언어의 답변에 곧바로 반영된다.

Financial Management orientation for Nepali students

재무관리 입문 · 네팔 유학생 오리엔테이션 →

네팔 유학생을 위한 영어 재무관리 입문 오리엔테이션 포털로, 재무관리를 한 번도 배운 적 없는 학생을 대상으로 삼는다. 카트만두의 작은 커피 회사가 100만 루피를 벌고도 통장에는 10만 루피밖에 없는 상황을 8부작 이야기로 따라가며, 재무제표 읽기부터 비율분석·화폐의 시간가치·채권과 주식 가치평가·자본예산·위험과 자본비용·자본구조와 배당까지 15주 과정 전체를 관통한다. 교수가 한국어로 말하면 gpt-5-mini가 약 1초 만에 영어와 네팔어 자막을 화면에 띄우며, 2026년 네팔 홍수 희생자를 위한 추모 페이지가 포털의 첫 화면이다.

Business Statistics Teaching Bot

Business Statistics Teaching Bot →

A LiveAvatar teaching bot that explains business-statistics concepts step by step — from basics to regression.

Math Study Room — Demand-Driven Math

Math Study Room — Demand-Driven Math →

Interactive math explained to each learner's needs — calculus, probability, game theory, DSGE, stochastic processes, and more.

AI Teaching & Counseling Bot Catalog

AI 티칭·상담봇 통합 카탈로그 →

연구실이 운영하는 티칭·상담·행정 봇을 한자리에 모은 카탈로그. 같은 서비스를 상용 API와 유료 아바타, 자체 GPU의 온프레미스 Gemma4, 비용이 들지 않는 학생 실습 경로의 세 가지로 구현해 두어 기술 선택의 차이를 나란히 견주어 볼 수 있다. 설계 이론과 단계별 자습서도 함께 정리했다.

RISE Startup-Curriculum Report

RISE Startup-Curriculum Report →

Research report on developing RISE entrepreneurship curriculum.

Counseling & Guidance Bots
AI Psychological Counseling Bot

AI Psychological Counseling Bot →

Trust-by-design avatar counselor for professional psychological counseling — age/gender-adaptive dialogue, a 4,076-chunk academic RAG corpus (KCI, PubMed/PMC, OpenAlex), real-time avatar with voice and vision, cross-session continuity, and a post-experience survey with a public results dashboard.

Elder-Focused AI Counseling Bot

Elder-Focused AI Counseling Bot →

A self-hosted counseling bot for older adults — retirement, health, loneliness, and family, grounded in a 2,313-chunk academic corpus (KCI) re-embedded locally with bge-m3. Same self-hosted avatar/voice stack as the CHA bot; the GPU brain runs on the lab's lumen server.

CHA Freshman Major-Counseling Bot

CHA Freshman Major-Counseling Bot →

A self-hosted AI interview assistant helping CHA freshmen navigate major and career choices — voice/text conversation with a live browser-rendered 3D avatar, grounded in 110 real department Q&A cards, running end-to-end on the lab's own GPU (no external avatar SaaS).

Global Business AI (GBA) Bot

Global Business AI (GBA) Bot →

AI assistant (avatar / voice / text) for CHA University's Global Business AI major.

Service

외국인 출입국 사무지원 RAG AI →

하이코리아 안내를 근거로 필요한 업무와 준비서류를 찾아주고, 하이코리아·1345·전자민원으로 연결하는 6개 국어 출입국 사무지원 AI입니다. 텍스트·음성·영상대화를 지원합니다.

Financial-Products Consultant

Financial-Products Consultant →

AI consultant across 11 categories and 72 financial products, with a navigable product catalog and voice / avatar modes.

CHA University Patent Bot

CHA University Patent Bot →

A LiveAvatar guide to the university patent filing process — walks through invention disclosure requirements and review deadlines, then builds a submission-ready invention description with you, section by section, exportable as docx.

University Administration AX
Academic Affairs AX Portal

Academic Affairs AX Portal →

All-in-one academic portal: student/faculty/TA chatbots (regulations · majors · graduation), department dashboard, unified approval inbox — plus system overview, prior-research review, and an always-on FGI evaluation survey.

Academic-Affairs TA Bot

Academic-Affairs TA Bot →

A LiveAvatar teaching bot for department teaching assistants — step-by-step guidance on real TA tasks (shared-credit consolidation, expense evidence, implementation plans, form collection, notices, approvals, counseling). Text, voice, and avatar modes.

CHA Curriculum Reform Decision Sheet

’27–’30 교육과정 개편 의사결정 시트 →

15개 학과·전공의 사전자료를 미리 읽어 두어, 전공만 고르면 바로 시작합니다. AI교육혁신원이 내려보낸 개편 원칙을 나열하고 현재 안이 어디까지 지키고 있는지 판정한 뒤, 모듈·교과목·전공능력이 어긋난 지점을 검토 항목으로 만듭니다. 채택·수정채택·보류·미채택·직접제안 5지선다와 자유 서술로 답하면, 그 결정을 원본 양식에 채워 넣은 hwpx 를 바로 내려받습니다.

AI-University Readiness Self-Assessment

AI-University Readiness Self-Assessment →

A self-diagnosis tool measuring readiness for an AI-centered university.

AX War Room

AX War Room →

An integrated AI-transformation (AX) command portal.

People

Advised Students

Graduate students advised by Prof. Dae Keun Park — all aspiring AI Healthcare Convergence Architects. The lab reaches across social sciences (business & economics), life sciences, rehabilitation (sports, psychology & art therapy), nursing, pharmacy & medicine, and engineering — studying generative AI that applies to every one of these fields.

Prof. Dae Keun Park
Principal Investigator
Prof. Dae Keun Park
CHA University · dkpark@cha.ac.kr
PhD Candidates · 4
Yu Seung Kim
Yu Seung Kim
Hyper-Personalization
Kyung Tae Kim
Kyung Tae Kim
Medical AI
Dae Hyun Kim
Dae Hyun Kim
Physical AI
Sang Hyun Cha
Sang Hyun Cha
AI Forecasting Modeling
M.S. Candidates · 8
Gyu Seong Lee
Gyu Seong Lee
AI Forecasting Modeling
Hyeong Gyu Choi
Hyeong Gyu Choi
AI Forecasting Modeling
Bong Ju Sung
Bong Ju Sung
Intelligent Bot Development
Jeong Ho Kim
Jeong Ho Kim
Psychology
Ji Hye Park
Ji Hye Park
Media Communication
Ye Won Choi
Ye Won Choi
Exercise Therapy
Yu Yeon Jang
Yu Yeon Jang
Exercise Therapy
Lingling Zhang
Lingling Zhang
Nursing
Vision

Direction & Vision

Toward a decision-support lab that treats generative AI as a default tool for research and teaching. (Draft — being refined.)

1

Generative-AI-native research

Use embedding-based analysis and LLM agents / domain-specific bots to support decisions in finance, policy, and healthcare.

2

Deeper convergence

Combine financial time-series forecasting with bio-computing, and sharpen structural-change detection and microsimulation with AI.

3

Research as a product

Turn published findings into deployable portals, dashboards, and chatbots — the live portals on aiforalab.com are the proof.

Ask the Lab

AI Assistant

Ask anything about the lab's research, publications, courses, projects, or vision. Korean and English both work.

AI
Lab Assistant
● Online
What does this lab work on?
Summarize the ESG-news research
Which AI-integrated courses are offered?
What is the lab's future vision?