Model trends: League 2, 12 Mar 2017

Regular readers will know that I churn out updated model predictions after every round of matches but I’m aware that there’s quite a lot of information in them and they can be difficult to track. I’m pretty keen to keep tabs on how well the model performs myself – not least because I’m constantly tinkering with it – so I’ve come up with a simple template that tracks how its assessment of each EFL club has evolved over the season.

The way it works is pretty simple: for pre-season and after every round of games it shows the results of my simulations for a specific club in terms of both:

  • How their average predicted final league position has changed (the solid line in the top chart)
  • How their predicted probability of ending up in each section of the table has changed (the coloured columns in the bottom chart)

The point of this is to show how the model’s assessment of a club’s prospects has changed after each round of games, but I also wanted some idea of how good a predictor it is. I’ve therefore added (as a dashed line) each club’s actual league position and briefly assessed (under each graphic) how well it’s predicted this so far.

I’m not expecting a 100% accuracy rate for a variety of reasons, including:

  • As Leicester recently reminded us, football is notoriously difficult to predict and the strongest team doesn’t always win
  • The rating system that drives the predictions can take a little while to adjust to sudden changes (e.g. a big tactical shift, replacing the manager or a lot of transfer activity)
  • While I’m pretty happy with the rating system and model, there’s limited data available in the lower leagues and therefore it may miss some subtleties in the way certain teams perform

Anyway, onto the graphics. There’s one for every team along with a brief summary and my view of how well the model’s predicted their fortunes.

After their impressive showing last season the model had high hopes for Accrington. While it didn’t factor in the loss of key players over the summer it would have adjusted pretty quickly if they began performing at a lower level, but the strange thing is that they picked up pretty much where they left off performance-wise. Unfortunately from late October a horrible run of form torpedoed any hope of another promotion challenge and now even a top half finish looks unlikey.

Model performance: far too optimistic and didn’t see their horrible run coming

The model predicted a mid-table finish for Barnet and it looks like that’s where they’re on course to end up. It maintained its optimism despite the Bees’ poor start and the extent of their recovery even provided hope of a play-off spot before some poor recent results made that unlikely.

Model performance: pre-season prediction looks pretty accurate

The model expected Blackpool to challenge for a play-off place this season and maintained that assessment until their frustrating run of draws saw their prospects ebb. However a few recent wins have bounced them back into contention and they’re just three points off a play-off place and their healthy goal difference stands them in good stead.

Model performance: pre-season prediction looks pretty accurate

Cambridge’s disastrous start didn’t dampen the model’s expectation of a mid-table finish too much and so their subsequent recovery wasn’t too surprising. Their performances have been improving for quite some time and they’ve been expected to finish in the top half since October. Even a play-off finish isn’t out of the question as they’d be just a point off seventh place if they win their game in hand.

Model performance: sustained optimism looks to have been justified

In pre-season the model expected a play-off finish from Carlisle – their strong attack has been undermined by a vulnerable defence – and that looks set to be realised. Despite spending a big chunk of the season in the top three, their recent collapse now makes it much more likely that they’ll end up outside it.

Model performance: pre-season caution looks to have been justified

Cheltenham’s convincing promotion campaign led the model to predict a safe mid-table finish, but they don’t appear to have adjusted as well as expected. There’s been a lot more flirting with relegation than anticipated and their ratings have steadily declined, although a few recent wins look to have done enough to keep them safe this season.

Model performance: too optimistic

Colchester were predicted to finish comfortably inside the top half and despite a poor run early in the season they look to be on track to do just that. An impressive recovery took them to the fringes of the play-offs but performances have been ebbing for a while now and they need a strong finish to force their way back into top seven contention.

Model performance: pre-season prediction looks pretty accurate

The model didn’t have high hopes for Crawley’s season and still doesn’t rate them particularly highly, but they look comfortably safe from relegation nonetheless. Lower mid-table looks their most likely destination, with the model’s expectation needing half a season to adjust accordingly.

Model performance: too pessimistic

Despite a promising first half of the season, spent mostly in the top half of the table, the model continued to predict that Crewe would finish their campaign in the lower half. Since mid-December that’s looked increasingly prescient and after a dip in both results and performances they’re sitting pretty close to where the model anticipated.

Model performance: pre-season prediction looks pretty accurate

Doncaster looked unlucky to have been relegated and the model’s pre-season prediction took that into account, pegging them for a top three finish. With automatic promotion having looked all but certain since the end of January, a return to League 1 looks to be well within their grasp.

Model performance: correctly predicted a title challenge

In pre-season the model assessed Exeter as being capable of a comfortable top half finish – and perhaps even a play-off challenge – and wasn’t unduly swayed by their poor start, which looked relatively unlucky. Their subsequent recovery has put them on course to achieve the model’s prediction and perhaps even surpass it.

Model performance: pre-season prediction on course to be fulfilled

Grimsby’s strong performance in gaining promotion was sufficient for the model to predict a safe mid-table finish and that looks a likely outcome. While the Mariners spent some time in the play-off zone earlier in the campaign, their performances have been more consistent with the mid-table area they now occupy.

Model performance: pre-season prediction looks pretty accurate

The model suspected that Hartlepool would have a relegation battle on their hands this season but fortunately some sharp finishing has kept them from being dragged into the bottom two so far. With six points between them and Leyton Orient, they’re likelier than not to avoid setting foot in the relegation zone altogether, but aren’t safe yet.

Model performance: relegation battle predicted in pre-season

Orient were expected to finish in lower mid-table by the model and that looked like a reasonable prediction in October, but the subsequent chaos surrounding the club has seen their fortunes worsen considerably. Relegation now looks very likely with six points separating them from safety.

Model performance: a shade too optimistic, although with mitigating circumstances

Luton were expected to challenge for promotion and they haven’t disappointed, although some more mixed results since the turn of the year has made a play-off finish far likelier than a place in the top three.

Model performance: promotion challenge proceeding as predicted

Mansfield were expected to finish in upper mid-table back in pre-season and despite some ups and downs that seems pretty accurate. Performances have improved since their January recruitment but a relatively modest goal difference may count against them in the race for a play-off spot.

Model performance: Pre-season prediction looks pretty accurate

The model’s assessment of Morecambe – particularly their defence – has been pretty negative since last season and it certainly didn’t see their positive start coming. While it was as unsustainable as predicted, they’ve continued to grind out enough points to remain above the relegation battle and now look to be headed for a comfortable mid-table finish.

Model performance: too pessimistic

Newport were expected to end up near the foot of the table, although without necessarily being relegated. However by mid-September the model had caught up with reality and began to forecast a less successful outcome, with the Exiles’ chances of relegation temporarily exceeding 50% as early as October, and despite a brief rally things now look very bleak indeed.

Model performance: predicted a battle against relegation, albeit initially a more successful one

When Notts County sat in the play-off zone in late October the model was still forecasting a relegation struggle based on the unsustainability of their performances. By the turn of the year things were looking bleak as predicted, but the appointment of Kevin Nolan has turned things around impressively. With an eight point cushion it would take a sizeable collapse to drag them back into danger.

Model performance: correctly predicted a relegation battle, although not the subsequent turnaround

Plymouth were expected to challenge for automatic promotion in pre-season and recovered from a slow start to do just that. They’ve looked likelier than not to finish in the top three since late September, although they’ve never been predicted to claim top spot even when occupying it for long periods. Performances look to have ebbed slightly this season, although results have remained sufficient to keep them comfortably in the top three.

Model performance: correctly predicted an automatic promotion challenge

Portsmouth were the model’s pre-season title favourites but have only just managed to break into the top three for the first time since September. Their strong ratings have kept the model optimistic of automatic promotion all season but their position remains far from comfortable in a tight battle. They need to start making their dominance count more regularly if they’re to avoid further disappointment.

Model performance: in automatic promotion contention, but not as comfortably as predicted

While Stevenage have made some steady improvements this season their recent surge into the play-offs has been surprising – at least to anyone looking at their data. Boro currently look like a solid mid-table side, which aligned with their league position as recently as February. It remains to be seen if they can sustain their improved form long enough for a promotion tilt but – in a division where seventh place is sufficient to make the play-offs – they certainly have a decent chance.

Model performance: didn’t see the late surge coming

Wycombe were expected to finish in mid-table and that prediction held despite a poor start, with their impressive run of results feeling like an overdue correction. Performances have ebbed since then and upper mid-table looks more probable than a top seven finish – thanks partly to their modest goal difference – which is a slight improvement on the model’s pre-season prediction.

Model performance: a shade too pessimistic

The model expected a lower mid-table finish from Yeovil and that looks set to be the case. Despite a brief incursion into the top half of the table – which didn’t move the needle on their anticipated finish all that much – they’ve mostly hovered around the predicted area of the table.

Model performance: Pre-season prediction looks pretty accurate