Artificial intelligence can automatically classify goods using HS coding methods.

How AI automates HS codeclassification and turns it The new reality of HS classification Classification hasbecome the controlpoint where cost, Your classification team receives an urgent alert: new tariffs take effect in 72 hours,impacting thousands of SKUs across multiple product lines. The regulatory changeaffects high-volume import categories that drive significant revenue. Your team needs to This scenario has played out repeatedly as regulatory volatility becomes the dominantreality facing global trade teams. The elimination of de minimis thresholds in certainimport lanes forced one electronics retailer to reclassify 12,000 SKUs within 45 days, avolume impossible to handle manually without significant outsourcing costs and errorrisk. Meanwhile, volatility in the application of Sections 232 and 301 tariffs, along with the It’s a challenging enough situation even for companies whose classification proceduresare airtight; imagine, then, how much worse the situation is for companies who havethousands of wrong or inconsistent classifications. This is no longer an operationalinconvenience, it’s a compounding supply chain risk. Classification errors flow directly intolanded cost miscalculations, sourcing strategy failures, compliance exposure, and speed- The acceleration of everything TheThomson Reuters® 2026 Global Trade Reportreveals the magnitude of thistransformation. Supply chain management has surged from 35% of professionals citingit as a priority in 2024 to 68% in 2026, nearly doubling in two years. Simultaneously, This convergence isn’t coincidental. U.S. tariff volatility, cited as the most impactfulregulatory change by 72% of trade professionals, represents just one pressure point.Teams simultaneously navigate export control expansions, EU Carbon Border Adjustment Classification has become the control point where cost, compliance, and speed converge. The strategic elevation of 155M+ tariff and classification datachanges published globally This pressure has fundamentally elevated classification’s strategic importance. Accurate •Duty calculations directly impact landed costs and financial projections•Compliance filings create audit exposure when they don’t match operational reality 100,000potential classificationdecisions from just 10,000 The scale alone makes manual-only approaches unsustainable. Modern portfolios spantens of thousands of SKUs across dozens of markets, with thousands of HS codesrequiring interpretation of similar language and country-specific nuances. When you factor As one global trade manager put it: “We went from managing compliance to enablingstrategy. Classification determines whether our procurement team can execute theirsourcing plans, whether finance can model scenarios accurately, and whether we can The four fault lines: Where manual These challenges tend to surface along four predictable fault lines. Fault line #1: Unmanageable scale Modern classification faces a complexity explosion that overwhelms human capacity: •Code proliferation: Thousands of HS codes with frequently ambiguous language requirecareful interpretation•Jurisdictional multiplication: The same product may require different optimal •Continuous change: New, split, or expired codes force ongoing reclassification acrossentire portfolios•Portfolio breadth: Large, multi-market product catalogs amplify workload exponentially The scale challenges exceed human capacity. A portfolio of 10,000 SKUs across 10markets creates 100,000 potential classification decisions. Add regulatory changes, new Fault line #2: Data quality crisis The “AI data qualityparadox”: bettertools on bad datadon’t solve the Data quality issues create cascading problems that undermine classification accuracy: •Inconsistent descriptions: Product names and attributes differ across systems, creatingresearch friction•Abbreviation confusion: Shorthand creates interpretation challenges and slows research This creates the “AI data quality paradox”: simply adding an “AI layer” onto messy datarisks accelerating inconsistencies rather than eliminating them. Fault line #3: Information bottlenecks Manual processes create information flow problems that impact cross-functional •Slow propagation: Classification updates reach finance, operations, and procurementtoo late for decision windows•Collaboration friction: Manual processes limit the frequency and quality of alignment Fault line #4: Reactive posture that multiplies risk Manual classification inherently operates in reactive mode: •Discovery delays: Issues surface after filings or during audits rather than duringdecision-making•No forward signal: Limited ability to predict which SKUs will be impacted as Together, these fault lines force organizations into a permanently reactive posture. The convergence effect 220+countries and territories ofharmonized tariff schedule These fault lines don’t operate in isolation, they compound exponentially. Scale pressuresworsen data qu