Live Simulation
Data: UNCTAD · World Bank · ITU · ADB
Total ASEAN-6 FDI
$79.6B
↑ 8.3% YoY · 2024E
AI Disruption Alerts
3
2 High Severity Active
Avg ESG Score
72.4
↑ 5.1 pts vs 2023
Forecast Accuracy
91%
30-day rolling avg
Nodes Monitored
127
↑ 12 this quarter

ASEAN-6 FDI Inflows 2015–2024

Source: UNCTAD FDI Statistics
Vietnam
Indonesia
Thailand
Malaysia
Philippines
Cambodia

Country Resilience Index 2024

Source: WB LPI + Oxford AI Readiness + ADB

Active Supply Chain Flow — ASEAN Corridor

Live
Node status updated by NLP disruption pipeline
SG
Singapore
Hub
→
PHTyphoon
Manila
Port ⚠
→
CERe-routed
Cebu
Alt. Port
→
HCMC
Ho Chi Minh
Assembly
→
PNG
Penang
Chip Fab
→
BKKDelay
Bangkok
Auto Tier-2
→
BKS
Batam
Mfg. Zone
→
JP
Tokyo
OEM
Operational
Warning
Critical
AI Re-routed
AI-Powered FDI Screening uses an XGBoost classifier trained on UNCTAD FDI statistics (2010–2024), World Bank Ease of Doing Business/LPI, ITU Digital Development Index, and Oxford Insights AI Readiness Index. Scores reflect investability for efficiency-seeking and technology-seeking FDI. Methodology: Belhadi et al. (2021); Mai (2025)

FDI Inflows by Country — Annual (USD bn)

UNCTAD FDI Statistics 2024

Sector FDI Composition 2023

ASEAN Investment Report 2024
Electronics / Tech
EV / Automotive
Semiconductor
Textile / Apparel
Logistics / BPO
Other

AI-Scored FDI Opportunity Matrix

XGBoost Model
Country Sector AI Score /100 WB LPI 2023 AI Readiness FDI 2024E ($bn) Risk Level ESG Grade Investability
Sources: UNCTAD (2024); World Bank Logistics Performance Index (2023); Oxford Insights Government AI Readiness Index (2024); ADB ASEAN Investment Report (2024)

Comparative Infrastructure Indicators

World Bank · ITU · WEF 2024
LPI Score (×20)
AI Readiness Index
Digital Dev. Index (×10)
NLP Signals / 24h
84K
GDELT + AIS + News
Forecast Horizon
2–8 wk
Ahead of disruption
Events Logged 2020–25
18
ASEAN-6 scope
Avg Impact ($bn)
$3.4B
Per major event

Historical Disruption Events — ASEAN Supply Chains 2020–2025

DateEventTypeCountries AffectedSeverityDurationEst. Trade ImpactRecovery Days
Sources: UNCTAD (2022, 2024); WTO Goods Barometer; IMF (2022); Samuels (2025); Roman et al. (2025)

Disruption Frequency by Country 2020–2025

Compiled from WTO, UNCTAD, IMF

4-Week Disruption Probability Forecast

NLP · BERT Pipeline
Signal sources: Maritime AIS (MarineTraffic), GDELT Project, procurement bulletins. Model: fine-tuned RoBERTa. Confidence interval ±8%
The Digital Twin module uses a Graph Neural Network (GNN) trained on tier-1 and tier-2 supplier relationships across ASEAN-6, with Monte Carlo stochastic disruption modelling (n=10,000 iterations per scenario). Reference: Roman et al. (2025); Dubey et al. (2021)

Scenario Library — What-If Simulation

GNN + Monte Carlo
Nodes Affected
0
Lead Time Impact
+0 days
Cost Exposure
$0
Recovery Estimate
–

Network State — Simulated Supply Chain

SG
Singapore
→
PH
Manila
→
VN
Vietnam
→
CN-SC
S. China
Supplier
→
MY
Malaysia
→
TH
Thailand
→
ID
Indonesia
→
EU/US
End Market

Scenario Cost Comparison

Monte Carlo mean estimate

Recovery Time Distribution

10,000 MC iterations, 90% CI
ESG scores derived from: LLM-parsed sustainability disclosures (GPT-4o pipeline), EcoVadis-format supplier audits, Sentinel-2 satellite land-use/emissions proxies, and blockchain-anchored certification records. E = Environmental, S = Social, G = Governance. Reference: Samuels (2025); Belhadi et al. (2021)
EU CBAM Ready
61%
↑ 14pp vs 2023
Scope 3 Coverage
78%
Tier-1 nodes
Blockchain Audits
1,240
Immutable records
Nodes with A+ ESG
23
↑ 6 vs last year

ESG Score by Country & Dimension

GRI + CDP + Satellite Data

EU CBAM Compliance Gap Analysis

EU Taxonomy 2024 criteria

Detailed ESG Scoring Matrix

CountrySector E ScoreS ScoreG ScoreOverall GradeCBAM StatusScope 3 TrackedBlockchain Certs
Sources: Global Reporting Initiative Disclosure Database (2024); CDP Supply Chain Programme (2024); Copernicus Sentinel-2 Imagery; EcoVadis Supplier Ratings Benchmark

Blockchain Compliance Ledger — Recent Audit Trail

Hyperledger Fabric
Permissioned blockchain governed under ASEAN Data Protection Framework. Records are tamper-proof. Hash prefix shown only. Full records accessible to consortium members.
Forecast model: ensemble of LSTM (sequence forecasting) and Prophet (seasonality decomposition), trained on 10-year ASEAN trade data. Disruption risk score integrates NLP pipeline signal strength. Stress scenarios modify demand elasticity and transit cost parameters. Reference: Dubey et al. (2021); Li et al. (2022)

12-Week Supply Chain Demand & Disruption Risk Forecast

LSTM + Prophet Ensemble
Low (20%)
Demand Index (left axis)
Disruption Risk Score (right axis)
Confidence Interval ±1σ

Country-Level FDI Forecast 2025

UNCTAD projection model

Scenario Sensitivity — Key Metrics

Stress slider affects all metrics below
This platform is grounded in empirical research from 7 peer-reviewed papers. Click any paper to expand the abstract. All papers are indexed in Scopus or Web of Science. The research proposal is submitted to ATTN Forum 2026, ISAS Singapore.

Research Methodology — Three-Phase Mixed-Methods Design

01
Platform Prototype Development + Expert Validation (n=25)
Functional prototype of 6-module AI platform: XGBoost FDI Screener, BERT disruption NLP pipeline, GNN Digital Twin, PPO reinforcement learning re-router, LLM ESG scorer, Hyperledger Fabric compliance ledger. Validated via semi-structured expert interviews with IPA officials and SC directors across ASEAN-6. Thematic analysis in NVivo.
02
Business Simulation Study + PLS-SEM (target n=300)
Controlled simulation: treatment group (AI platform) vs. control (conventional tools) navigating a compound disruption scenario. Performance measured across time-to-awareness, re-routing cost efficiency, recovery speed, and expert-evaluated decision quality. Survey instrument adapted from Belhadi et al. (2021), Dubey et al. (2021), Li et al. (2022). SmartPLS 4 for SEM; CR, AVE, HTMT validation.
03
Panel Data Regression — ASEAN-6, 2010–2024
Two-way fixed-effects panel model (country + year FE). Data: UNCTAD FDI Statistics, World Bank LPI, ITU Digital Development Index, Oxford AI Readiness Index, CDP ESG scores. Endogeneity addressed via 2SLS IV strategy (distance-weighted regional AI adoption rates as instruments, following Mai 2025). Robustness: System GMM, LASSO, heteroscedasticity-robust SEs clustered at country level.