Botmaster Jeremy Lichtman’s Sudan conflict deaths forecast, June 20, 2025

How many state-based conflict deaths in Sudan will be reported by ACLED for 2025?

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

* Less than 1000: 5%
* Between 1000 and 3000: 12%
* Between 3000 and 5000: 19%
* Between 5000 and 8000: 25%
* Between 8000 and 12000: 32%
* More than 12000: 25%
6–8 minutes read

Obtaining outside data.
Checking internet sources, using keywords: Sudan conflict deaths 2025
News from various sources:

Obtaining outside data.
Checking internet sources, using keywords: ACLED conflict deaths Sudan 2025
News from various sources:

The conflict in Sudan, which began in April 2023 between the Sudanese Armed Forces and the Rapid Support Forces, has led to significant underreported deaths according to recent studies. The London School of Hygiene & Tropical Medicine (LSHTM) conducted a study estimating that in the first 14 months of the conflict, over 61,000 people died in Khartoum State alone—a 50% increase in the pre-war death rate. Of these, 26,000 deaths were directly attributed to violence, a figure significantly higher than the 20,178 intentional-injury deaths reported for the whole country by the NGO Armed Conflict Location and Event Data (ACLED).

The LSHTM report highlights that deaths from the conflict have largely gone undetected, and that prevention and starvation were major causes of death across most of Sudan. The Kordofan and Darfur regions were particularly affected by violence. Researchers also found that collecting accurate casualty numbers has been challenging due to a lack of raw data and the complexity involved in obtaining it.

In terms of indirect deaths caused by factors such as preventable diseases and lack of emergency care, estimates suggest these are much higher than direct conflict deaths. Using past data from other conflicts, estimates range from 62,000 to 130,000 total deaths in the Sudan conflict.

The conflict has also resulted in the world’s biggest hunger crisis, with 25 million people at risk and aid organizations warning of a historic hunger crisis. The humanitarian situation in Sudan is further complicated by the breakdown of healthcare infrastructure, targeted attacks on medical facilities, and widespread hunger, with children being some of the worst affected.

There have been accusations of both conflict parties using starvation as a weapon against civilians, and international efforts to cease the conflict have been hindered by political disagreements, such as Russia’s veto of a UN resolution for a ceasefire.

Overall, the study’s findings underscore the hidden and severe impact of the conflict on Sudanese lives, emphasizing the need for increased international aid and efforts to end the violence.

Fact-checking news summary:
Fact-check did not return a result. Using news summary.

OpenAI gives a base rate of probability (Carolyn‘s note: OpenAi failed to return a value.)
The question difficulty is rated 7 (0 to 10)
Historical weighted factors include:
Historical conflict death rates, 0.2
Reported death tolls from similar conflicts, 0.3
Indirect death estimates from infrastructural collapse, 0.5
A Bayesian calculation could be performed as follows:
Assuming a prior probability based on historical factors (0.75), integrate recent news (61,000 deaths in 14 months) and indirect estimates (62,000 to 130,000 total deaths) which boosts likelihood to around 0.8.
Bayesian base rate: 0.8

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: 300

The following were considered in order to produce this base rate:
The base rate was determined by analyzing the severity and duration of the Sudan conflict, the reliability of death toll reports, and comparable situations in historical conflicts. The LSHTM data indicates a significant number of unreported deaths which influence the base rate.

Ideally, the news feed would contain the following sorts of information for a better forecast:
For a high quality forecast, further detailed and unbiased reports on ground conditions and humanitarian efforts in Sudan would be helpful. Access to improved and real-time data collection would also enhance forecast accuracy.

Some potential divergent considerations that might affect the base rate:
Improvement in political stability or successful international intervention could significantly reduce the mortality rate. Better data collection and healthcare aid could decrease the rate of indirect deaths.

The following chain of events are necessary for the question to resolve positively:
– Continued conflict in Sudan similar to current intensity High
– Consistent challenges in obtaining accurate mortality data Moderate
– Sustained high rates of indirect deaths due to starvation and lack of healthcare High

Querying Claude (Error: Claude is not returning an array)

Querying Mistral (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.14, “Between 5000 and 8000”: 0.3, “Between 8000 and 12000”: 0.35, “More than 12000”: 0.15] – confidence: 6)

Querying OpenAI (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.1, “Between 5000 and 8000”: 0.2, “Between 8000 and 12000”: 0.29, “More than 12000”: 0.35] – confidence: 7)

Question Type: Multiple Choice
Confidence: 6.5
MAPD: Avg: 0, Max: 0
# LLM responses: 2
Explanations of the above statistical measures here —>

Model value:
* Less than 1000: 5%
* Between 1000 and 3000: 12%
* Between 3000 and 5000: 19%
* Between 5000 and 8000: 25%
* Between 8000 and 12000: 32%
* More than 12000: 25%

The AI assessments agree that the ongoing conflict in Sudan has led to severe underreporting of deaths, as evidenced by studies like the LSHTM report which estimated significant fatalities in Khartoum State alone. The crisis is exacerbated by issues such as starvation and inadequate healthcare infrastructure due to the prolonged nature of the conflict and political instability. Although international efforts have been made, political disagreements have hindered resolutions, contributing to a grim outlook on mortality rates, with expectations of over 12,000 deaths in the current year being high. However, these predictions could change if political stability improves significantly, international interventions are successful, or if advancements in healthcare aid and data collection occur, all of which could lead to a reduction in both direct and indirect deaths from the conflict.

Runtime: 250 seconds

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

Below, a forecast of state-based conflict fatalities for Sudan in the VIEWS machine forecasting competition, which is an aggregate of the forecasts of twenty machine learning competitors. Our botmasters, Phil Godzin and Jeremy Lichtman, are conducting a side experiment in collaboration with VIEWS. The VIEWS aggregate forecast is much lower than ours.