Date China takes major military action against Taiwan – By Dec 2036
Loading…
(a) at least 1,000 People's Liberation Army military personnel have been deployed to the main island of Taiwan for the purpose of establishing PRC sovereignty;
(b) the People's Republic of China has imposed a blockade that closes all major Taiwanese ports (Kaohsiung, Keelung, Taichung, and Taipei) for at least 10 consecutive days; or
(c) the People's Republic of China has launched kinetic strikes (missiles, airstrikes, or naval bombardment) against military or civilian infrastructure on the main island of Taiwan.
Exclusions: military exercises that do not actively intercept traffic or strike targets; cyber-only operations; actions limited to outlying islands (Kinmen, Matsu, Penghu) without action against the main island; economic sanctions or trade restrictions without physical military action.
Bars include events up to their close, 23:59:59 UTC: “By end of Apr 2026” includes everything up to 30 Apr 2026, 23:59:59 UTC.
Built from historical cases only. Old, high-stakes territorial claims rarely turn into war (about 0.6% a year), and China has not invaded, blockaded or struck Taiwan in 77 years. Past buildups that ended in action mostly did so within a decade; the PLA's last reorganisation is about that age, lifting the line to 14% by late 2033.
Reference classes
- High-salience territorial claims at least 15 years old: years in which a war over the claim began (ICOW, 1816-2001, Americas, Europe, Middle East): 6 of 1057
- The same claims in their first 15 years: 7 of 577
- Territorial disputes that stopped at a blockade or a deadly attack without becoming a war, per war (COW MID 5.0, 1816-2014): 14 per 54 wars (4 blockades, 10 attacks)
- Military buildups by a claimant power that ended in military action (corrected: Aegean dropped, India-Kashmir and Turkey-Cyprus coded to this question's event): 9 of 12
- Action within 10 years of a buildup starting (Kaplan-Meier): 67%
- Buildups still without action after year 14 (China-Taiwan, Korea, Essequibo): 0 actions in about 171 case-years
- China-Taiwan's own record: years since 1949 with an invasion, port-closing blockade or strike on the main island: 0 of 77
Method
Reference classes
We use three levels of evidence, from general to specific, combined with partial pooling to estimate a time-varying monthly hazard rate.
Level 1: General territorial dispute base rate
Among all major-power territorial disputes post-1945, roughly 1-2% per year escalate to significant military action. This comes from the Correlates of War MID dataset (~2,400 militarized interstate disputes 1816-2014, 85% of fatal conflicts involving territorial issues). This is the weakest prior — just a sanity floor.
Level 2: Major powers with active military buildup for a specific territorial goal
This is the core reference class. We identified 13 historical cases — 8 that resulted in military action, 5 where no action has been taken despite decades of tension.
Cases that resulted in military action:
Cases where no military action has been taken:
Kaplan-Meier survival analysis of these 13 cases gives roughly 54% probability of action within 10 years of active buildup starting, implying an average annual hazard of ~7.5%/year during the buildup phase. The median time to action among those that acted was ~6 years.
The cases where no action was taken are critical — they show that roughly 40% of these disputes simply never result in full military action, even over many decades. China-Taiwan itself is the longest-running such case at 77 years.
Level 3: China-Taiwan specific expert data
Current prediction markets and expert surveys (as of March 2026) provide the most directly relevant evidence:
- Metaculus: full-scale blockade by 2030 at 40%, by 2035 at 60%; full-scale invasion by 2028 at 10%, by 2030 at ~20%, by 2035 at ~33%
- CSIS 2024 survey: 52% of 64 China experts think force short of invasion “likely” within 10 years; only 27% of US experts and 17% of Taiwan experts believe China can currently execute an amphibious invasion
- Swift Centre: 9% blockade probability by mid-2027
- Pentagon 2025 report: PLA targeting capability to fight and win a Taiwan war by end of 2027; new bridge landing vessels and expanded amphibious training observed
These imply annualised hazard rates of ~12-16%/year near-term (peaking 2027-2028 around the PLA modernisation milestone), declining to ~7%/year long-term.
Multilevel model
The posterior annual hazard rate for each year is a weighted average of Level 2 and Level 3:
λ_pooled(year) = 0.80 × λ_specific(year) + 0.20 × λ_group
- 80% weight on Level 3 (specific): prediction markets aggregate hundreds of forecasters with diverse information — substantially more informative than the small historical sample.
- 20% weight on Level 2 (group): the reference class pull prevents overconfidence and anchors the long-run tail to historical base rates.
Level 1 is absorbed into Level 2 (the Kaplan-Meier already incorporates the non-action cases).
Time variation
The hazard rate is time-varying: it peaks in 2027 (the PLA's stated modernisation deadline, the consensus “window of maximum danger” identified by military analysts) then gradually declines as the specific risk window passes. It remains well above the general base rate throughout the forecast horizon due to the structural nature of the cross-strait dispute. Monthly values are smoothed via linear blending at year boundaries, then converted to a cumulative CDF via the survival function.
Hazard rates and cumulative probabilities by year
Resolution criteria
This market resolves to the earliest date at which any of the following conditions is reported by at least two of AP, Reuters, and AFP: (a) at least 1,000 People's Liberation Army military personnel have been deployed to the main island of Taiwan for the purpose of establishing PRC sovereignty; (b) the People's Republic of China has imposed a blockade that closes all major Taiwanese ports (Kaohsiung, Keelung, Taichung, and Taipei) for at least 10 consecutive days; or (c) the People's Republic of China has launched kinetic strikes (missiles, airstrikes, or naval bombardment) against military or civilian infrastructure on the main island of Taiwan. Exclusions: military exercises that do not actively intercept traffic or strike targets; cyber-only operations; actions limited to outlying islands (Kinmen, Matsu, Penghu) without action against the main island; economic sanctions or trade restrictions without physical military action.
Sources
- Metaculus Q#11480: Chinese invasion of Taiwan forecasts
- Metaculus Q#12309: China blockade of Taiwan forecasts
- Metaculus Q#5320: Chinese control of half of Taiwan by 2050
- Metaculus Q#11401: China controls Taiwan after invasion
- CSIS ChinaPower 2024: expert survey on China's approach to Taiwan
- CSIS ChinaPower 2022: earlier expert survey (64 China experts)
- Swift Centre: China-Taiwan and TSMC risks to 2027
- Pentagon 2025 Report: annual report on PRC military and security developments
- UI Sweden (2024): “Is a conflict over Taiwan drawing near?” — review of available forecasts
- EA Forum (2023): “An invasion of Taiwan is uncomfortably likely”
- Correlates of War: Militarized Interstate Disputes dataset (base rates)
Download the Python script used for this analysis
Refitted again on 17 November 2026 under the house rule that the line comes from reference classes only. v1's Level 3 (prediction markets and expert surveys, 80% of the weight) is removed, and so is the 2027 peak: no reference class was found linking a stated military deadline to when action came. Level 1 is now measured, not assumed: in the ICOW territorial claims data, high-salience claims at least 15 years old saw a war over the claim begin in 6 of 1057 claim-years (0.57% a year), against 7 of 577 in their first 15 years. This question also counts a 10-day closure of the main ports or strikes on the main island, so blockade-only and attack-only disputes are added from the COW MID data: 4 blockades and 10 attacks with over 25 deaths per 54 territorial wars, giving a background of 0.71% a year.
Level 2 is the corrected 12-case buildup set, coded to this question's event: Greece → Aegean dropped (it runs the other way), India → Kashmir coded as action in 1947 → 1948, and Turkey → Cyprus as action in 1964, when Turkish jets struck the island. No case acted after year 14, so the hazard is matched to the age of the buildup with a cure model (a share of buildups act after an exponential wait; the rest never do). Taiwan's age is dated two ways with equal weight: from 1949, as v1 and the other open cases are coded (age 77, extra risk near zero), and from the PLA's 2016 reorganisation into theatre commands, as the Crimea case is dated from Russia's 2008 military reform (age 11, about 4.8% in the next year, falling). The line is conditional on no qualifying action by 17 November 2026.
Level 2: Major powers with active military buildup for a specific territorial goal
| Case | Buildup start | Action year | Time to action |
|---|---|---|---|
| China → Tibet | 1949 | 1950 | 1 years |
| Indonesia → East Timor | 1974 | 1975 | 1 years |
| Iraq → Kuwait | 1988 | 1990 | 2 years |
| Argentina → Falklands | 1976 | 1982 | 6 years |
| Russia → Crimea | 2008 | 2014 | 6 years |
| Turkey → Cyprus | 1964 | 1974 | 10 years |
| India → Goa | 1947 | 1961 | 14 years |
| Russia → Ukraine (full) | 2014 | 2022 | 8 years |
Checked against sources, November 2026.
| Case | Buildup start | Duration so far |
|---|---|---|
| China → Taiwan | 1949 | 77+ years (ongoing) |
| N. Korea → S. Korea | 1953 | 73+ years (ongoing) |
| Venezuela → Essequibo | 1966 | 60+ years (ongoing) |
Checked against sources, November 2026. Removed as wrong: India → Pak Kashmir; Greece → Turkey Aegean.
Hazard rates and cumulative probabilities by year
| Year | Annual hazard (pooled) | Cumulative P(action by year-end) |
|---|---|---|
| 2026 | 7.9% | 7.0% |
| 2027 | 15.9% | 20.7% |
| 2028 | 14.3% | 32.1% |
| 2029 | 12.7% | 40.6% |
| 2030 | 10.3% | 46.8% |
| 2031 | 8.7% | 51.4% |
| 2032 | 7.1% | 55.0% |
| 2033 | 7.1% | 58.2% |
| 2034 | 7.1% | 61.1% |
| 2035 | 7.1% | 63.9% |
Sources
Liquidity over time
i Shows the market’s available liquidity over time. Liquidity can decay continuously and may change discretely if liquidity adjustments are applied.2 comments
Log in to comment.
AEI/ISW (November 6) assess this may be a major unannounced exercise simulating Taiwan's isolation, larger than Justice Mission 2025: surface groups from the Eastern, Northern and Southern Theater Commands, the Liaoning group, and the Fujian seen leaving Sanya on November 2. AEI/ISW
The G7’s November 11 declaration singled out Chinese operations east of Taiwan as a danger to regional stability and shipping. It reiterated opposition to coercive or forceful changes to the status quo. G7 declaration