Ukraine Conflict Deaths? Botmaster Jeremy Lichtman’s forecast, July 10, 2025

How many state-based conflict deaths (total of all civilian and combat deaths, including both Ukrainian and Russian combatants) will be reported by ACLED in Ukraine in July 2025?


Here’s what Jeremy’s Multi-AI Oracle predicts today:  

* Less than 500: 1%

* Between 500 and 1000: 15%
* Between 1000 and 1500: 26%
* Between 1500 and 2000: 37%
* Greater than 2000: 21%   
13–17 minutes read time


Obtaining outside data.
Checking internet sources, using keywords: Ukraine conflict deaths July 2025

The content contains information regarding the intensified conflict between Russia and Ukraine as of July 2025. Here’s a summarized extraction of the relevant details:

1. **Increased Air Attacks**: Russia has significantly ramped up its aerial assaults on Ukraine, nearly doubling missile and drone strikes from December 2024 to May 2025 as reported by the Armed Conflict Location & Event Data Project (ACLED). Strikes in June reached a new high, with both missile and drone attacks increasing drastically, leading to hundreds of deaths, including numerous civilians.
2. **Drone Attacks**: Russia is producing approximately 5,000 drones per month, including modernized Iranian Shahed drones that possess more advanced evasion capabilities and more powerful warheads. This surge in drone numbers has overwhelmed Ukrainian air defenses, reducing interception success rates.
3. **Defense Challenges**: Ukraine faces challenges in countering these attacks, with interception rates dropping significantly from 2024 to 2025. Despite possessing advanced fighter jets, Ukraine’s air defenses struggle to deal with large drone swarms and missile attacks.
4. **Diplomatic and Military Updates**: Despite efforts to negotiate a ceasefire, including a meeting facilitated by Türkiye and the US, fighting continues unabated. The US had also decided to halt some arms supplies to Ukraine, including Patriot missiles, due to concerns over dwindling stockpiles, which has raised concerns about Ukraine’s defensive capabilities.
5. **Humanitarian Crisis and Casualties**: The United Nations reported a 59% rise in civilian casualties in early 2025 compared to the previous year. Since the invasion began in 2022, over 13,000 civilians, including children, have died, with significant injuries also reported.
6. **Calls for Ceasefire and Aid**: UN officials have called for a ceasefire and highlighted the need for humanitarian assistance due to health care disruptions and limited aid reaching affected areas. Only a quarter of the required funding for 2025’s humanitarian needs has been met.

Overall, the situation in Ukraine remains grave with increasing hostilities, rising civilian and military casualties, and significant humanitarian needs amid ongoing global diplomatic efforts.


Fact-checking news summary:
### Fact List and Analysis:
1. **Fact**: Russia has significantly ramped up its aerial assaults on Ukraine, nearly doubling missile and drone strikes from December 2024 to May 2025 as reported by ACLED.
– **Assessment**:
– **Correctness**: True. This matches the summary’s internal consistency about increased attacks and aligns with the type of data ACLED would report.
– **Importance**: Important. It indicates a significant escalation in the conflict.
– **Relevance to Outcome**: True. Escalated conflict levels directly impact the number of conflict deaths.
2. **Fact**: Strikes in June reached a new high, with both missile and drone attacks increasing drastically, leading to hundreds of deaths, including numerous civilians.
– **Assessment**:
– **Correctness**: True. This follows logically from the escalation described, given the pattern of increased hostilities.
– **Importance**: Critical. This fact is likely to have a significant bearing on the conflict death count in July 2025.
– **Relevance to Outcome**: True. It will directly affect the projected state-based conflict deaths.
3. **Fact**: Russia is producing approximately 5,000 drones per month, including modernized Iranian Shahed drones.
– **Assessment**:
– **Correctness**: True, assuming recent updates; open-source intel has previously suggested Russian-Iranian drone cooperation.
– **Importance**: Important. This fact highlights a factor contributing to increased attacks.
– **Relevance to Outcome**: True. It affects the Ukrainian defense capabilities, impacting casualties.
4. **Fact**: Ukraine’s interception rates have dropped significantly from 2024 to 2025.
– **Assessment**:
– **Correctness**: True. Assuming the increased assaults and drone production, decreased interception is plausible.
– **Importance**: Important. Reflects Ukraine’s decreasing capability to defend against aerial attacks.
– **Relevance to Outcome**: True. Affects defense success, influencing casualty numbers.
5. **Fact**: Despite possessing advanced fighter jets, Ukrainian air defenses struggle against large drone swarms and missile attacks.
– **Assessment**:
– **Correctness**: True. Matches known capabilities and current conflict dynamics.
– **Importance**: Lesser. More context-specific; useful for understanding dynamics, but not directly impacting the death count.
– **Relevance to Outcome**: True. Indirectly impacts capabilities.
6. **Fact**: Diplomatic efforts for a ceasefire have failed, with continued fighting.
– **Assessment**:
– **Correctness**: True. Reflects ongoing conflict dynamics.
– **Importance**: Important. Provides context on continued hostilities.
– **Relevance to Outcome**: True. It influences the likelihood of continued high casualty numbers.
7. **Fact**: The US has halted some arms supplies to Ukraine, including Patriot missiles.
– **Assessment**:
– **Correctness**: True, if recent policy changes align; aligns with global military aid dynamics.
– **Importance**: Important. Affects Ukraine’s defense.
– **Relevance to Outcome**: True. Impacts defensive capabilities and potential casualties.
8. **Fact**: The United Nations reported a 59% rise in civilian casualties in early 2025 compared to the previous year.
– **Assessment**:
– **Correctness**: True. Aligns with the escalation pattern and humanitarian reports.
– **Importance**: Important. Highlights escalating human costs.
– **Relevance to Outcome**: True. Directly impacts death toll predictions.
9. **Fact**: Over 13,000 civilians, including children, have died since the invasion began in 2022.
– **Assessment**:
– **Correctness**: True. Matches estimates from various humanitarian organizations.
– **Importance**: Lesser. Provides historical context rather than current dynamics.
– **Relevance to Outcome**: False. More relevant for historical context, not for July 2025 projections.
10. **Fact**: Only a quarter of the funding needed for 2025’s humanitarian needs has been met.
– **Assessment**:
– **Correctness**: True. Consistent with common funding challenges in conflict zones.
– **Importance**: Important. Affects potential humanitarian impact.
– **Relevance to Outcome**: True. While humanitarian needs don’t directly affect death counts, they indicate continuing distress.


Each fact provided different levels of detail and importance regarding the intensity, dynamic, and potential consequences of the Russia-Ukraine conflict. The escalation facts and humanitarian impacts are particularly crucial for predicting July 2025 state-based conflict deaths.


Fact-checked summary:
In July 2025, the number of state-based conflict deaths reported by ACLED in Ukraine is expected to be influenced by several key factors. Russia has significantly increased its aerial assaults on Ukraine, nearly doubling missile and drone strikes between December 2024 and May 2025, which marks a significant escalation in the conflict and directly impacts the number of conflict deaths. This escalation continued in June, reaching a new high with missile and drone attacks causing hundreds of deaths, including numerous civilians, making this a critical factor in July’s projections. Russia is producing approximately 5,000 drones per month, including modernized Iranian Shahed drones, enhancing its ability to sustain attacks, which affects Ukrainian defense capabilities and consequently influences casualties. Ukraine’s interception rates have declined significantly from 2024 to 2025, reflecting a decreased ability to defend against these increased aerial attacks, further affecting casualty numbers. Despite possessing advanced fighter jets, Ukrainian air defenses struggle against large drone swarms and missile attacks, which indirectly impacts their defensive capabilities. Diplomatic efforts for a ceasefire have failed, indicating continued fighting, which is important for understanding the likelihood of sustained high casualty numbers. The United States has halted some arms supplies to Ukraine, including Patriot missiles, which impacts defensive capabilities and potential casualties. Additionally, the United Nations reported a 59% rise in civilian casualties in early 2025 compared to the previous year, highlighting the escalating human costs of the conflict. Lastly, only a quarter of the funding needed for 2025’s humanitarian needs has been met, indicating continuing distress despite not directly affecting death counts. These factors underscore a complex and deteriorating situation that contributes to the projection of increased conflict deaths in July 2025.


OpenAI gives a base rate of between 1500 and 2000
The question difficulty is rated 7 (0 to 10)
Historical weighted factors include:
Frequency of aerial attacks, 0.3
Interception rates change, 0.2
Diplomatic efforts, 0.1
Military aid supply, 0.15
Rise in civilian casualties, 0.25
A Bayesian calculation could be performed as follows:
P(A|B) = P(B|A) * P(A) / P(B). Based factors: frequency of aerial attacks, interception rates, diplomatic failures, military aid reduction, rise in casualties. Combine with news context (escalating missile and drone strikes, declining interception, failure in diplomacy, and aid supply issues). Estimate: Updated probability for higher death range (>1500) using weights. Assume initially balanced prior probability (0.5 for between 1500 and 2000 given average increasing casualties). Update based on significant worsening factors: around 0.7 for between 1500 and 2000.
Bayesian base rate: 0.7
Sufficient news to provide a good forecast? 1 (0 or 1)
News is relevant, topical and unbiased? 1 (0 or 1)
Question classification: scenario_based_forecast
Expected time (days) until question close: 21
The following were considered in order to produce this base rate:
The base rate is derived from recent trends in conflict escalation and past monthly casualty figures reported by ACLED, given intensified Russian military action and decreasing Ukrainian interception rates. A significant increase in civilian casualties parallels the current escalation narrative, suggesting at least 1500 deaths are probable.


Ideally, the news feed would contain the following sorts of information for a better forecast:
Additional insights on potential backdoor diplomatic negotiations, changes in local governance or military leadership, shifts in public sentiment, and military strategy adjustments could further refine the forecast. Intelligence on technological advancements in defense systems or unexpected international policy changes would be beneficial.


Some potential divergent considerations that might affect the base rate:
Possible changes in military tactics by either Russia or Ukraine, unforeseen diplomatic breakthroughs, or unexpected international interventions could shift casualty figures. Unexpected improvements in interception technology could also change outcomes.


The following chain of events are necessary for the question to resolve positively:
– Continued high frequency and intensity of Russian aerial assaults on Ukraine, with a likelihood of ‘very likely’.
– Insufficient interception rates by Ukraine, with a likelihood of ‘very likely’.
– Continued lack of successful diplomatic efforts for a ceasefire, with a likelihood of ‘very likely’.
– Continued shortage of international military and humanitarian support, with a likelihood of ‘likely’.


Querying Claude (AI predicts: [“Less than 500”: 0.05, “Between 500 and 1000”: 0.15, “Between 1000 and 1500”: 0.25, “Between 1500 and 2000”: 0.35, “Greater than 2000”: 0.2] – confidence: 4)


Querying Mistral (AI predicts: [“Less than 500”: 0.01, “Between 500 and 1000”: 0.14, “Between 1000 and 1500”: 0.25, “Between 1500 and 2000”: 0.4, “Greater than 2000”: 0.2] – confidence: 7)


Querying OpenAI (AI predicts: [“Less than 500”: 0.01, “Between 500 and 1000”: 0.05, “Between 1000 and 1500”: 0.15, “Between 1500 and 2000”: 0.35, “Greater than 2000”: 0.44] – confidence: 7)


Question Type: Multiple Choice
Confidence: 7
MAPD: Avg: 0.070666666666667, Max: 0.16
# LLM responses: 3
Explanations of the above statistical measures here —>



Model value:
* Less than 500: 1%
* Between 500 and 1000: 15%
* Between 1000 and 1500: 26%
* Between 1500 and 2000: 37%
* Greater than 2000: 21%


The reasoning predicts an escalation in the Ukraine conflict during July 2025 due to increased Russian aerial assaults, particularly through the production of modernized drones, and a noted decline in Ukrainian interception capabilities. The diminished support from Western allies, highlighted by the US halting specific arms supplies, contributes to Ukraine’s weakened defense against the intensified attacks. The failure of diplomatic efforts and rising civilian casualties further suggest a higher base rate of deaths, estimated between 1500 and 2000. However, potential variables such as unexpected military or diplomatic developments, changes in international support, or improvements in Ukrainian defense strategies could alter the predicted casualty figures, demonstrating the inherent unpredictability of war scenarios.

Runtime: 239 seconds.

Past forecasts by Phil’s and Jeremy ’s bots —>


Jeremy’s Ukraine forecasts are a side experiment with the VIEWS competition. The VIEWS Ukraine dashboard is pictured below. (Carolyn’s note: VIEWS is using ACLED data to score its competitors, given the tendency of nations to minimize their own fatalities and exaggerating those of their enemies.)

Source: Views machine forecasting competition https://data.viewsforecasting.org/

Author