How many seats will the Conservative Party win in Canada’s April 28, 2025 parliamentary election?
Here’s what Jeremy Lichtman‘s Multi-AI Oracle forecasts today:
* less than 172: 33%
* between 172 and 205: 44%
* between 206 and 240: 17%
* more than 240: 6%
Jeremy’s note: Mismatch between numeric and textual summary results today for the election question!
Carolyn’s note: The Conservative Party must win at least 172 seats to gain control of the Parliament without needing to build a coalition with one of the smaller parties.
Here’s how Jeremy’s Multi-AI Oracle says it arrived at these probabilities: Obtaining outside data.
Checking internet sources, using keywords: Canada Conservative Party election seats
Results from around the web:
Okay, the user is asking for current web results related to the Canada Conservative Party election seats. Let me start by looking through the provided search results to find relevant information.
First, search result [1] from Wikipedia mentions the 2025 Canadian federal election, noting it’s using a new 343-seat map. That’s important because it sets the total seats and context for the Conservative Party’s targets. The writs were issued on March 23, 2025, so the election is imminent.
Search results [2] and [4] (which seem to be duplicates from YouGov) provide a detailed projection. They predict the Liberals winning a majority of 20 seats. Specifically, the Conservatives are expected to lose some seats to the Liberals in Ontario, like Bay of Quinte and Niagara ridings, but gain seven seats from the NDP. However, overall, the Conservatives might not gain as much as needed for a majority. This is crucial for the user’s query as it directly addresses seat projections for the Conservatives.
Result [3] lists candidates but doesn’t provide specific seat data, so maybe not as relevant. Result [5] discusses prediction markets but doesn’t mention Canada’s election, so probably not useful here.
The user asked for tables. From the YouGov data, I can extract the seat changes. The Conservatives are projected to lose seats in certain areas but gain in others. Creating a table comparing projected seat changes would help. Also, the total seats for each party based on the projection would be useful. Since there’s no time series data in the sources, I can’t include that, but I’ll note its absence.
URLs to cite are [1], [2], and [4] (even though they’re duplicates, maybe just cite [2]). Need to check if any other sources mention prediction markets, but result [5] is about prediction markets in general, not specific to this election. So, maybe exclude that unless the user wants general info, but the query is about current data. So stick to [1], [2], [4].
Wait, the user also asked for market prediction sites like Kalshi, but none of the provided results include those. The user might need to know that info isn’t available here. So, in the answer, mention that no data from prediction markets was found in the provided sources.
Now, structuring the answer: start with a summary of the election context, then the projections, create a table for seat changes, another for total seats, and list the URLs used.
The 2025 Canadian federal election, scheduled for April 28, will use a new 343-seat electoral map based on the 2021 census[1]. Current projections from YouGov’s MRP model suggest a competitive race, with the Liberal Party poised to secure a modest majority of 20 seats, while the Conservative Party faces mixed regional outcomes[2][4].
### Conservative Party Seat Projections
**Key Battlegrounds and Shifts:**
– **Gains from NDP:** Conservatives are projected to gain **7 seats** from the NDP, including ridings in British Columbia and the Prairies[2][4].
– **Losses to Liberals:** The party is expected to lose seats to the Liberals in Ontario’s **Bay of Quinte** and both **Niagara Ridings** (Niagara Falls—Niagara-on-the-Lake and Niagara South)[2][4].
– **Quebec Dynamics:** Only **1 seat** is projected to shift from the Bloc Québécois to the Conservatives, despite Liberal gains of 11 Bloc seats[2][4].
#### Seat Changes Table
### Limitations
No data from prediction markets (e.g., Kalshi, Polymarket) was found in the provided sources, limiting analysis to polling-based projections[2][4].
**Sources:**
[1] [2025 Canadian federal election – Wikipedia] (https://en.wikipedia.org/wiki/2025_Canadian_federal_election)
[2] [YouGov MRP Projection] (https://yougov.co.uk/politics/articles/52054-first-yougov-mrp-2025-canadian-federal-election-shows-liberals-on-track-to-win-modest-majority-poll)
[4] [YouGov Analysis] (https://today.yougov.com/politics/articles/52054-first-yougov-mrp-2025-canadian-federal-election-shows-liberals-on-track-to-win-modest-majority-poll)
OpenAI gives a base rate of (Carolyn’s note: OpenAI failed to return a value. See the Bayesian base rate below.)
The question difficulty is rated 7 (0 to 10)
Historical weighted factors include:
Previous performance of the Conservative Party in federal elections, 0.3
Current polling trends favoring the Liberal Party, 0.4
Impact of recent policy decisions by the Conservative Party, 0.1
Voter turnout patterns, 0.2
A Bayesian calculation could be performed as follows:
Utilize the historical factors table where each factor updates prior probabilities based on weightings and incorporate the likelihood of current events (polling trends showing Liberal advantage). Use Bayesian updating to adjust the base rate considering these weighted factors.
Bayesian base rate: 0.3
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: 4
The following were considered in order to produce this base rate:
The base rate is generated by considering past election cycles where the Conservative Party secured a significant number of seats, and integrating current polling data which suggests a Liberal advantage. The Conservative Party’s historical ability to adapt in elections was difficult to factor in due to a lack of analogous situations in the provided data.
Ideally, the news feed would contain the following sorts of information for a better forecast:
Ideally, data from prediction markets or insider political analysis could provide further clarity on seat distribution shifts. Also, more granular turnout data and regional policy effects would help refine the seat projections.
Some potential divergent considerations that might affect the base rate:
Changes in voter sentiment after recent local debates or national events could influence the outcome significantly. Also, unexpected factors like economic changes or shifts in policy focus affecting swing voters might not be captured in current projections.
The following chain of events are necessary for the question to resolve positively:
– Conservative Party gains a majority of seats in the 2025 Canadian federal election Unlikely
– Conservative Party gains significant seats in Ontario, reversing the projected losses to the Liberals Unlikely
– Conservative Party gains additional unexpected seats from the NDP and Bloc Québécois beyond current projections Somewhat unlikely
Querying Claude (AI predicts: [“less than 172”: 0.75, “between 172 and 205”: 0.2, “between 206 and 240”: 0.04, “more than 240”: 0.01] – confidence: 6)
Querying Mistral (AI predicts: [“less than 172”: 0.3, “between 172 and 205”: 0.5, “between 206 and 240”: 0.15, “more than 240”: 0.05] – confidence: 6)
Querying OpenAI (AI predicts: [“less than 172”: 0.3, “between 172 and 205”: 0.4, “between 206 and 240”: 0.25, “more than 240”: 0.05] – confidence: 6)
Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.16666666666667, Max: 0.3
# LLM responses: 3
Model value:
* less than 172: 33%
* between 172 and 205: 44%
* between 206 and 240: 17%
* more than 240: 6%
Multiple AI-generated summaries highlight that current polling and historical trends suggest the Conservative Party is unlikely to secure a majority in the upcoming election. Most predictions show them losing crucial seats to the Liberal Party in key Ontario and Quebec ridings, making it difficult to surpass the 172-seat mark required for a modest majority. The Liberals are projected to secure a majority with around 172 seats, given their strong positioning in critical regions. However, several scenarios could upset these predictions, such as last-minute shifts in voter sentiment due to scandals, effective Conservative campaign strategies, changes in voter turnout patterns, or unexpected national or economic events that could favor the Conservatives.
Guide to Jeremy’s Bots Reports (These don’t all apply to the current version of his bot.)
MAPD: Mean Absolute Percentage Deviation calculates the average percentage difference between actual values and predicted values, providing a relative measure of error.
Median: We collect the output values from the LLMs in an array. We then take the median value. This is between 0 and 1 (i.e. 0.15 = 15%).
Base rate: Currently we take OpenAI’s value as the base rate. We are working on a better value using a different prompt that takes into account process. The base rate helps to determine if the median makes sense.
SD: The standard deviation between the median and the base rate.
Confidence: We query each of the LLMs on how confident they are of their predictions (between 0 and 10) and take a median. Because the LLMs tend to be overconfident, we take anything lower than 6 as being low confidence. This factors into the overall model.
Conf Mode: Based on the confidence value. >=9 is high confidence. Below 6 is low confidence (this is also triggered by an exceptionally high SD).
Mellers: This refers to Barbara Mellers, specifically a paper she wrote that includes a formula for moving values towards an extreme (i.e. 0 or 1).
Reverse Mellers: This uses the formula from above, but with a sub-1 coefficient to move the values closer to 50%.
Theory of Mind: We ask the LLMs what they think other LLMs would predict. We hope that this makes them consider the questions more deeply.
Beta Distribution: Currently unused, but possibly of interest. This is based on the median, the base rate and the SD.
Close Type: We noticed that the appropriate base case for some questions is closer to the extremes, while others are closer to 50%. When we have a low confidence value, this helps us to determine whether to extremize or de-extremize the value. ‘A’ implies closer to zero. ‘B’ implies closer to 50%. ‘C’ implies closer to 100%.
# LLM Responses: The count of LLMs that responded. We query 5 currently, but they have a relatively high API failure rate.
Model value: For normal confidence mode, this is the median. For high confidence, this is the Mellers value. For low confidence, this is either the Mellers or Reverse Mellers (depending on the Close Type).
