Skip to content
Matchup DNAUpdated recently

Magda Linette v Janice Tjen, Chennai Open

HardWTA TourFinalBest of 3Completed

Magda Linette

Seed 3Won

44.9%

Janice Tjen

Seed 1Favourite

55.1%

Final score 5-7 6-1 6-4

Tournament start → round-awareLinette 44.9% → 42.4%(−2.5 pts)Tjen 55.1% → 57.6%(+2.5 pts)Two separate stored forecasts, not a continuous update
Uses only information from before the tournament began.phase4-ts-v1Issued Scored forecastHow the models differ

Why the model leans this way

Tournament start
← favours Linettefavours Tjen →

Hover or focus a bar for its exact value and the inputs behind it.

The bars add up to log-odds of -0.205 for Linette, which is Linette 44.9% and Tjen 55.1%. No effect here: time since last match, missing serve data, unranked.

Log-odds are the model's own units; near 50%, 0.1 is about 2.5 percentage points. Inputs overlap (overall and surface Elo especially), so one bar is not that input's independent effect, and none of this is a cause.

Player comparison

As the model saw them
LinetteTjen
1607
Elo
1588
1592
Surface Elo
1621
57.1%
Service points won
59.0%
41.7%
Return points won
39.9%
−23 pts
Form vs Elo
+6 pts
7
Days since last match
7
476
Rated matches
58

Values stored with this forecast, as the model saw them. Bars compare the two players on each row; rows use different units, and rows that can be negative show values only.

Forecast history

Every stored version
  1. Tournament startTjen 55.1%Scored
  2. Round-awareTjen 57.6%Scored

Filled points are the scored (first-issued) forecasts; hollow points are later revisions. Points are separate stored forecasts, not a continuous line.

VerificationStored before the scheduled startCode matches the frozen protocol#7, #8 in the ledgerShow records
Tournament start · issued
Prediction id
c629308c92d52ee2ffccc1ebb262493097db2dff497595a49f5c463b4d193900
Inputs (SHA-256)
bea3fb874aa449edbc6b68043e9e6fa0e95a8fdfe9e79a9686ca88d3cf18f52b
Model artifact
a34233a3876d89fe3cd70c782b0d0a31de9192ad0895e05332c7bb5a93fd246c
Code
21911efc3219c875e35155290de8ff29c257e182e5c9b99785cc99daa58981e8
Ledger
position 7, chain hash 6b1b661d3aae6763cf19b1f461af38c9c28e1e484c62f6fdc90162e7fadce041
Round-aware · issued
Prediction id
9993c808da9bbd15922b3ea764e113291a3e7c9b15cb97a5ef6b4ed680fa823b
Inputs (SHA-256)
3e837f4e614c815851e9d1cd6be3d34445151381ec65b0480317ce74879a8840
Model artifact
1121f09ca231aab60e0040a11dbbc2f48282ef525341971c93f28465756f7e5f
Code
21911efc3219c875e35155290de8ff29c257e182e5c9b99785cc99daa58981e8
Ledger
position 8, chain hash 18a6f846769a76f83b8fae297ae13eb648d0401fd41014d6a07e254da1c1d4f8

Decision log

  • Tournament start: Forecast issued.
  • Tournament start: Checked again: inputs unchanged, so no new forecast.
  • Round-aware: Forecast issued.
  • Round-aware: Checked again: inputs unchanged, so no new forecast.

Result reported by ESPN; each source is stored separately and a disagreement is never scored.

These checks show that a forecast was recorded before the match and has not changed since. They say nothing about whether it was right; that is what the Model Lab measures. Every forecast is also listed in the Forecast Archive.