METHODOLOGY

The method behind every QPV valuation.

Five principles, one repeatable method, every valuation. Here is what we measure, how we weight it, and how we prove it six months later.

01 / METHODOLOGY

Standardised inputs, not surveyor intuition.

Every QPV valuation is decomposed into the same six factors every time. No freeform adjustments. No 'sunset premium' or 'harbour view plus 8%' invented on the spot. Every factor has a defined weight derived from Hong Kong transaction data.

01

Comparable transactions

Recent sales of similar units in the same building or neighbouring blocks. Top 30 selected by similarity score.

02

Building age

Year of completion. Older buildings adjusted against renovation status and structural depreciation.

03

Floor level

High floor, mid floor, low floor. Premium and discount weightings derived from transaction data per district.

04

Unit size

Saleable area in square feet. Non-linear pricing curve calibrated per district.

05

Unit condition

AI-scored from public listing photos. Six-band scale, fully overridable with audit trail.

06

Transaction recency

Time decay on comparable weighting. Recent sales weight more heavily than older ones.

Risk teams get a repeatable input signature. Banks get a methodology that can be reviewed, not a narrative. Reviewed six months apart, the same inputs give the same output within tolerance.

02 / METHODOLOGY

Every valuation shows its drivers.

A QPV valuation is not a number. It is a number with its reasoning visible: which comparable transactions were selected, how they were weighted, which features moved the estimate up or down, and by how much. Click any valuation and the audit trail opens.

This matters for three groups. Bank risk committees approving loans. Regulators reviewing portfolio exposure. Sellers understanding why their property is valued at HK$11.2M and not HK$11.8M. No black box.

03 / METHODOLOGY

Uncertainty is information.

Every QPV output is a band: HK$10,780,000 to HK$11,700,000 with a point estimate of HK$11,240,000 and a +/-4.1% confidence range. The band widens when comparable data is sparse, ages with market volatility, and tightens when fresh transactions stack up in a district.

Banks underwrite against the low end of the range, not the point estimate. Sellers price against the high end. Regulators see both. False precision is more dangerous than honest uncertainty.

04 / METHODOLOGY

Reproducible six months later.

Every valuation records its inputs, weights, comparables, photo-condition scores, market-condition flags, and output. The record is stored immutably. Six months later, a different team can replay the same inputs and get the same output. This is a hard requirement for bank-grade valuation.

For institutional valuation use cases, audit trail is not optional. For mortgage origination, it is the difference between a loan approved and a loan denied. For sellers, it is proof the number was not negotiated into existence.

05 / METHODOLOGY

Built for Hong Kong, not retrofitted.

QPV is trained exclusively on Hong Kong transaction data from 2024 onwards, sourced through the 2025-launched Land Registry API. Building stock is classified by HK typology (public estate, HOS, private estate, walk-up, single block). Regulatory context aligns with HKMA, HKIS, and Basel III as implemented in HK from 1 January 2025. A global AVM retrofitted to HK would miss the district-level nuances that drive 30%+ price variance.

Coverage spans 35+ HK districts, with thousands of transactions analysed and AI-scored from listing photos. Coverage grows daily as new transactions settle.

QUESTIONS

What people ask.

Why quantitative methods?

Market risk teams in banks value thousands of financial assets every day using a consistent logic: decompose every asset into its drivers, apply defined weights, compute a price with a confidence interval, record the audit trail. We apply that logic to Hong Kong property. Both are priced from comparable transactions, both have explainable drivers, both demand reproducibility.

How do you measure accuracy?

QPV targets PPE10 of 70%+: seventy percent of valuations land within 10% of the actual sale price. Industry benchmarks for mature Western AVMs sit at 80-90% PPE10. Our 70%+ target is intentionally conservative for a prototype working from an early-stage HK transaction dataset. With full Land Registry integration, we target 85%+ within 12 months.

What data do you use?

Hong Kong Land Registry transaction records from 2024 onwards (via the 2025-launched Land Registry API). Building-level and district-level metadata from our own platform layer. AI condition scoring from public listing photos. We do not use any non-public data sources. Every valuation can be reproduced from public inputs plus QPV's proprietary models.

NEXT

See the methodology in action.

Walk through a sample valuation report or speak with the team about your portfolio.

Learn more: About QPV and Sweven Limited