A.I IN AFL PART 3/3

Last week Sam Mitchell caused quite a stir when he admitted to using AI in his coaching process and although what was reported contained very limited detail of what he actually uses and what he uses it for, the uproar was ridiculous.

There is no doubt that AI will become a part of Aussie Rules in the near future as team's are always looking for ways to optimise and streamline their approaches and there's not an easier way to do that then through AI means.

On Twitter I came across this comment on the subject which of course sent me down the rabbit hole of this 341 page study titled "Artificial Intelligence-Based Decision-Making Support During Australian Football Matches" and here is part 3 of 3 of my numerous notes from it.

• AI prediction of match outcomes study
• Can machine learning models based on technical performance and not score margin, predict match outcome in real time?
• All models performed well (73.5 – 75.8% prediction rate) v benchmark score-based model (77.4%) with accuracy being at its lowest at the start of the match (45.7 – 48.8%) and increasing to peak near the end of a match (87.2 – 92.7%)
• A DSS is a computer system designed to support the decision making of the user
• A handful of technical PI’s are able to predict match outcome from 78.9 – 95.1% but the models weren’t designed for in-game us, only pre/post-game
• Wanted to test other metrics but scoring-based one’s and opted for meters gained, meters gained per kick, time in possession, inside 50’s, turnover’s, time in forward half, contested possession, effective disposal, groundball gets, marks on lead and rebound 50's
• Defensive stats x 1v1 losses, rebound 50 differential, tackles, 1v1 wins, spoil differential
• Transition stats x intercept from mark, defensive 50 rebound to boundary %, defensive 50 ball movement to wing %, defensive 50 ball movement to corridor %, turnover’s
• Offensive stats x inside 50’s, repeat inside 50’s, uncontested marks, initial inside 50’s, leads targeted, scoring accuracy
• Data should guide you with what to do, not just tell you what to do
• Suggestions were made for it to dig deeper so they added an insights option which provided breakdowns of the subcategories of PI’s contributing to the broadly defined PI’s which formed the suggestion and the coaches liked it
• What might be best is a combined approach where coaches provide a list of specific changes they might make during the game or have made before, coupled with their pre-conceived expectations of the way these would impact the values of their PI’s and instead of suggesting numerical PI targets, the AI could then suggest a small selection of these specific changes which would satisfy the teams needs according to the coach’s preconceived expectations and then the coach picks the most appropriate change in the moment
• Long term, data can be collected on the actual impact of these changes and this database could be used to provide more objective actionable suggestions
• Decision-making stages AI could support include opportunity trigger, understand the opposition, determine the need for action, explore options, evaluate the decision
• Impact AI could have on decision-making constraints x manage information volume, reduce emotion, reduce time pressure, prompt early coach reaction, direct focus
• An AI-based DSS should update regularly, be easy to navigate, use color, be customisable, be transparent in its confidence, provide the ability to manually dig deeper
• Coaches respond to an opportunity trigger, they endeavour to understand the opportunity and then determine the need for action
• If action is required, coaches explore options, take action, and then evaluate the decision
• AI can handle far more information in time-constrained environments than humans and can pick up on patterns not recognised by the coach
• Coaches should consider opportunities within current in-game decision-making/coaching practice’s where they would be willing to be supported by AI and communicate this with those responsible for building the DSS, use the discovery of context specific decision-making processes as an opportunity to reflect on your own practice by asking yourself: h
• How am I becoming aware of an opportunity?
• Am I truly considering the underlying cause of the opportunity before deciding?
• Is taking action always necessary and how do I assess whether action is necessary?
• Where am I sourcing my options from and am I leaning on the experience of others around me to support the exploration of options?
• How/when do I take action and is my message getting across to the right people in an effective manner
• How do I evaluate whether a decision was the right one?
• The discovery of context specific decision-making constraints during matches serves as an opportunity to minimise some of these constraints through means other than AI so ask yourself:
• Are there any ways that I can improve the way I communicate my thoughts to players/assistant coaches?
• What impact does emotion have on my ability to make good decisions and how can I be more objective
• What are the most important pieces that I want to be fed during games and have I communicated this effectively to my coaching team/support staff?
• Work closely with analysts to find common ground on the types of DSS based solutions you think could be useful and provide feedback on any barriers you face when using the DSS
• Give a DSS time to evolve, communicating with the developer about what would help build trust in the system
• For analysts you are the conduit between the DSS and the coach and its effectiveness will depend on your communication of suggestions from the DSS to the coach, work closely with the person designing the DSS and provide suggestions for improvements + understand the underlying processes/technique involved so you can adequately explain suggestions
• For researchers/practitioners/analysts aiming to design/develop/implement a DSS to gain an in-depth understanding of how coaches make decisions in their environment, you need to:
• Build a DSS that fits their current processes
• Consider ways to incorporate additional data types to improve on the current method
• Work closely with coaches/analysts and consider the implementation of a DSS as a continuous process
• Ensure the suggestions the DSS provides are sufficiently actionable for the coach
• Be willing to compromise on perfect science to provide a DSS coaches will find most useful
• Any new system will be competing for attention so incorporate desirable functions of older/pre-existing systems into the new DSS

BRISBANE v CARLTON PRACTICE GAME ANALYSIS

Interesting game for a practice hit out last night.

For me I wanted to look at Brisbane's ball movement which I covered in detail here in which I will be constantly referring to in any Lions videos this year.

My best mate is a Blues supporter so I'm somewhat interested in them as I have to watch them live a couple of times a year when he comes up but also a local boy from down my way and an ex-teammate's son Taylor Byrne was playing so I was very keen to see what he would do and he didn't disappoint - kicking 3/.1 all in the last quarter to get the Blues over the line. 

This will be broken up into a Brisbane part and then a Carlton part.

BRISBANE

After going through numerous Brisbane games late last year, and same as watching/analysing Sydney and Collingwood games previously, it's impossible not to watch them play and pick up on the trends I've identified in their respective products (Sydney, Collingwood).

In Brisbane's case it's short kick possession football, patience with the ball, hit up leads and getting length towards goal of which all of these are touched on in the video + the companion video I alluded to.

CARLTON

As mentioned in the video the Blues are a big work in progress as they turn their list and game style upside down and this video shows a clip of the "good/new" Carlton but then the "old/crap" Carlton rears its ugly head as well which will be their vibe this season I think but at least there's a conscious effort to change unlike previous years of going to the contest well over and over again.

For full access to this game analysis, register for a level 1 membership from https://aussierulestraining.com/membership-account/membership-levels/.

A.I IN AFL PART 2/3

 

Last week Sam Mitchell caused quite a stir when he admitted to using AI in his coaching process and although what was reported contained very limited detail of what he actually uses and what he uses it for, the uproar was ridiculous.

There is no doubt that AI will become a part of Aussie Rules in the near future as team's are always looking for ways to optimise and streamline their approaches and there's not an easier way to do that then through AI means.

On Twitter I came across this comment on the subject which of course sent me down the rabbit hole of this 341 page study titled "Artificial Intelligence-Based Decision-Making Support During Australian Football Matches" and here is part 2 of 3 of my numerous notes from it.

• Information that needs to be collected from coaches before building a suitable DSS are what's your background/experience? How long were in each position? How did they lead to your current role? What different types of decisions do you make during games? Why do you see them as important/necessary? What factors impact those decisions? What information do you rely on to make game decisions? How does that information help you do that? Do you use either internal or external sources of information? Describe a specific decision you made in a game and the process behind it? How did you identify the problem? What did you do next? How did you evaluate the decision
• Opportunity Trigger refers to data, coach observation, intuition and momentum
• Momentum can be identified through objective (you can see it) and subjective means (a change in pivotal stats, quick shifts in scoring, field position etc)
• Understand the Opposition refers to looking for context, experience, using data as evidence and involves searching for more detail/why is it happening to make an informed decision
• Coaches will use data to reassure what they’re seeing is correct
• Determine the Need for Action refers to the fact coaches can’t control some things and sometime doing nothing is the best method as players play well or play bad in any given game which is again out of the coaches control
• After an uncontrollable factor causes a problem, it’s better to consider the players intention in the moment and keep going
• A key aspect of a head coach’s decision making is to find the balance between when to and when not to change things up and where that balance lies may depend on the coaches philosophy/belief in the capacity of the players to solve a problem on their own even though a lot of coaches favour immediate performance benefits over valued learning outcomes for players during games
• In the end, the determination for or against change either halt the decision-making process (no change) and reassess layer or change (proceed to the next stage)
• Explore Options refers to sourcing options, action types, weighing up the value of action
• Coaches want to hear the ideas of others in this phase of decision making
• Coaches will rarely do things they haven’t at least talked about during preparation
• When you solve 1 problem then another opens up – there’s a cost to every decision
• When selecting an option that is good enough there is a tendency to go beyond picking the next best option and through explicit consideration/calculation or risk/reward, the exploration of options represents a coach’s best attempt at reasoning within their constraints
• Take action refers to the head coach having final say + frequency/timing of decisions
• The coach's role is to facilitate the decision-making process collaboratively and they then must filter all the information and then assume sole responsibility to make the call
• Avoid sending messages out in the last 5mins of a quarter so you can properly deliver it at the break
• Evaluate the decision refers to the fact that not every decision is right + consequences of getting decisions wrong + time to evaluate
• You'll rarely win from making the right decision/s but you can definitely lose if you make the incorrect ones
• You have to allow time for 1 change to work before making another
• Coaches can make rapid, pre-emptive decisions to allow a more considered decision to come later which is 2 subsequent decision-making processes (1 rapid/1 extended) where the evaluation from rapid leads into extended
• Barriers to A.I decision-making study
• To minimise decision-making constraints, you could develop/implement a DSS system
• Information that needs to be collected beforehand includes what barriers to effective decision-making do coaches face during games? What are the thoughts/perceptions of coaches towards A.I based DSS’s during games? What are the visual functional design elements which would enable coaches to utilise/interpret information provided by a DSS?
• A hypothetical might be a scenario where we're down at half time, we don’t know what’s going wrong or what can fix to improve our chances of winning
• At half time we use the DSS by adding in instance 1, import live data, observe interface and then read the suggestions
• You'll also be able to navigate the simulator tab and play with a stats toggle to simulate what different changes in your stats will do to your predicted chance of winning
• Barriers to decision-making include cognitive deficits via coaches emotion, delayed reactions/misdirected focus
• Environmental deficits via time pressure, difficulty in communication, the physical environment (up in the coaches box v on the bench) and information volume
• Cognitive barriers to decision-making constrain the decision-making process internally via coaches experience and cognitive limitations
• When emotion develops into a barrier then you need to catch your breath and stop and look the wall/have a drink to shift your mind away from what you’re actually seeing
• Coaches expressed they sometimes identified potential options but refrained from implementing them due to their concern that their communication of the message would be ineffective
• Without a collaborative, calm environment, the ability to make decisions in a rationale/collaboratively way is hindered and there’s less psychological safety around incorrect decisions
• Coach Thoughts/Perceptions on DSS included an un/willingness to adopt (replacement/hesitancy), expectations (ease of use/what coaches want), concern/criticism (oversimplicity/overreliance), the actual DSS role (when and how/who and why)

A.I IN AFL PART 1/3

                                                      

 

Last week Sam Mitchell caused quite a stir when he admitted to using AI in his coaching process and although what was reported contained very limited detail of what he actually uses and what he uses it for, the uproar was ridiculous.

There is no doubt that AI will become a part of Aussie Rules in the near future as team's are always looking for ways to optimise and streamline their approaches and there's not an easier way to do that then through AI means.

On Twitter I came across this comment on the subject which of course sent me down the rabbit hole of this 341 page study titled "Artificial Intelligence-Based Decision-Making Support During Australian Football Matches" and here are my numerous notes from it.

• During games coaches face limitations to available information and cognitive capacity (calculating risk/reward)
• A decision support system takes complex computational methods and empowers the user with them in an interactive/easy to use manner
• Can pinpoint in-game performance indicators and their relationship to success in that specific game
• Phase 1 x exploration of in-game decision-making of AFL coaches
• Phase 2 x develop a decision-support systems (DSS) to leverage AI/Performance Indicator’s (PI's) predicated on the insights gained from phase 1 to support coach in-game decision making
• Phase 3 x deployment/implementation of dss with AFL clubs to evaluate DSS impact
• Decision making is intertwined within the coaching process in both participation/performance settings
• Coaching is built on a cyclical relationship between information, knowledge, skills of the coach, athlete's capabilities, performance analysis, competition and preparation, all that require elements of decision making
• The need to make complex decisions to fit the problem at hand may result in some parts of the coaching process receiving more attention than others
• Coaches employ naturalistic decision making, consulting common sense models developed through experience with the premise of decision making being that decisions emerge from a subconscious process of scanning the environment, recognising a decision problem (a mental threshold is triggered) and consulting knowledge stored as mental models without explicit reasoning resulting coaches using mental simulation/consultation of previous matching decisions from decisions in time=pressured situations
• All decision making requires ongoing situational assessment that triggered some form of action which suggests that there is more to coaching than experience/intuition and it relies on the idea that the formulation of decisions still rests heavily on the cognitive processes of coaches
• Coaches should consider their decision-making environment
• In complex situations, individuals trying to make rational decisions (based on reasoning) usually end up making satisfactory ones but not the optimal one because rationality is constantly bound to the interactions of cognitive/environmental constraints = suboptimal/inconsistent decisions with making the right decision being heavily dependent on the information available and how well a coach interprets it
• Cognitive constraints (memory, heuristics, knowledge, problem solving ability) + environmental constraints (sport science, assistant coaches, performance analysis, athlete monitoring technology, available information) = rational decision making capabilities
• Inconsistent decisions will be made based on instinct alone
• Coaches need to consult with both cognitive/environmental constraints to make informed decisions
• Machines can process larger/more complex loads of information than humans and more rapidly
• Human data collection can be inconsistent from different interpretations
• PI’s are quantitative measurements of action variables that aim to define different aspects of performance and they should form the basis of analysis
• Research in AFL found that winning teams were different to losing teams with regards to 14 out of 16 analysed PI’s including greater values for kicks, handballs, marks, inside 50’s, un/contested possessions and tackles
• In AFLW, PI's were disposal efficiency, kicks, marks and uncontested possession = winning
• Coaches can use data to make decisions to maximise/minimise certain PI’s
• Rather than using PI’s to compare un/successful performances, use PI’s to group players into positional roles
• PI’s related to ball winning, ball use, hit outs, defense and negative performance can allow coaches to identify players of a desired positional role while supporting recruitment/selection decisions
• Feedback can be categorised by valence (positive/negative), prescriptive (information on how to change performance)/descriptive (described performance) + content/audience
• Post-game feedback retention from players is low possibly from being ineffectively delivered and it is more often descriptive v prescriptive which allows athletes to self-regulate their response to feedback in a way that is conducive to learning
• Rather than trying to immediately correct performance, the coach is afforded time during the week to consider the best way to correct performance through further feedback/training design
• Pre-competition feedback should be targeted towards decision-making by facilitating knowledge creation so they need to allow players to solve problems independently while guiding them in the right direction
• Training is the time to manipulate the quantity of feedback to develop problem solving abilities with pre-post competition feedback focusing on providing players information they need to form their own decisions
• AFL has a runner to deliver messages with 81.3% being prescriptive and 58.4% were controlling in nature where coaches pressured players to think/act in a certain way = a higher proportion of prescriptive feedback v other sports
• Coaches send out 15 messages/quarter with the highest amount coming at times when the game is undecided and significantly lower in games when the game was "over"
• Expert decision makers recognise cues/patterns quicker than novices but are still limited by the information processing capacity of humans and machine learning can combat these limitations by finding patterns that the coach doesn’t have time to and decreasing the need to analyse raw stats and have more time to apply expert judgement with a higher standard of information than previously
• Decision trees classify outcomes by splitting the data on features that provide the most information about an outcome until splits can no longer be made such as meters gained relative to turnover’s forced score relative to time in possession relative to win/loss + meters gained relative to turnover’s force score relative to win + meters gained relative to turnover’s forced score relative to disposals to win/loss
• Trees terminate the splitting process when a selected information threshold/tree length is reached
• Of 97 PI’s available for analysis, decision tree model accuracies were as high as 88.9% for finding the most important PI’s to winning being meters gained, inside 50’s per shot on goal, turnover’s forced score and time in possession
• Although accurate/easy to interpret, they can be too simple to provide great insight into performance
• Via a generalised linear model, score margin was predicted on average within 7.4pts with the most important measures being inside 50’s per shot, inside 50’s and rebound 50’s
• Converted to win/loss outcomes, generalized linear model sits at 95.1%
• Technical PI’s can explain performance just as good as tactical PI’s but tactical provides a more unique insight into performance
• Cognitive constraints (coach's perception, memory of events, philosophy, opinions) + environmental constraints (live match stats, athlete monitoring technology, information from assistant coaches) + suggestions from decision support system all go to the coach's mind = decision is made and communicate to players
• To make a DSS these question’s needing to be answered include how do coaches make decisions in competition, what barriers to effective decision making do coaches face during games, what are the thoughts/perceptions of coaches towards the use of AI-based DSS’s during  games, what are the visual/functional design elements which would enable coaches to utilise/interpret information provided by a DSS, how efficacious are score agnostic models for the prediction of end-match outcomes in games, which variations and what type of model is the most useful for supporting coaching decisions during games, when implemented in the field what is the impact of an in-match DSS on coach decision making during games, how does the way a DSS is used change throughout an implementation, what are the elements of a DSS or its implementation process which contribute (positively/negatively) to the uptake of the system…
• In-game decision making consists of 6 stages x opportunity trigger, understand the opportunity, determine the need for action, explore options, take action, evaluate
• Bounded rationality, an extension of rational choice, describes the process that coaches employ to make decisions with the outcome of the decision dependent on the interaction between the available information, their own cognitive limitations/biases and the finite time in which they have to act and given the same decision making prob, it explains how different coaches can come to different right decisions
• Coach decision making study - bounded rationality highlights the benefit in having access to the best possible information/environment with masterful mental capabilities (perception, knowledge, metacognition) when making decisions
• A common framework for understanding the decision making of sport coaches is naturalistic decision making and it explains that in time-constrained decision making environments, expert coaches will scan for/attend to key attractors/recognisable patterns in a continuously unfolding environment, framing a decision problem if a mental threshold is reached
• Key attractors immediately lead expert decision makers to a simply matched solution in most cases though they search for additional cues to diagnose the problem if an immediate solution is not recognised
• In some cases, a stored solution may not match the present problem leading to mental simulations of potential modifications to solutions from previous experiences to evaluate their applicability to the present problem
• Coaches have more time to make their decisions in v players/umpires and therefore can engage in more critical reasoning

STATE OF ORIGIN GAME ANALYSIS

Footy is here and it's about time.

I think most of us weren't sure how this game was going to look and turn out to be but rest assured it was more than worth it, and something that can easily work in the long term.

On paper the Vics looked ridiculous and not that WA were any slouches themselves, but a midfield group of Bont, Butters, Diacos with a secondary unit of Serong, Merrett, McCluggage, Richards, Anderson and Rowell is stuff All-Australian teams are made of.

After a fast start for WA, they couldn't quite complete their numerous comebacks but the game was definitely competitive and how the AFL decide to rill with this going forward is anyone's guess.

When this was first announced might thought was to rotate teams as much as possible so that it's not always the Vics and then players like Bont/Daicos who would be in it every year start skipping years because the shine has worn off. If states plays every 3 - 4 years or so then that's 1, maybe 2 opportunities to represent your state so the hunger will be there every time it presents itself.

Unfortunately to make this a commercial success I suspect the AFL want it to be (and that's usually all they're interested in), they'll need the Vics in it 80% of the time.

From this game we look at:

• Richards Wing Run
• Buying Your Time for Your Midfielders to Reconnect
• Jackson Midfield Run
• Greene Exploiting the Stand Rule
• Gawn Takes His Defender
• WA Fat Side Line

A NEW TRAINING TOOL OF MINE

 

When you're still (trying) playing open-age footy at 47yrs of age then you'll search high and wide for anything that a) makes it easier to do so, and, b) could still provide additional performance benefits.

I have followed David Weck for a while now and although a little eccentric, it's probably passion more than anything else.

He has a very specific twist on performance training, having previously invented the Bosu Ball, of which I have one at home from years ago.

His latest product is the Pulse Power Vest that I received earlier this week and took it for a test spin yesterday of which I detail in this Twitter thread.

It wasn't cheap to get all the way over here to Melbourne but for an old athlete like myself, its potential for performance gains or at least maintenance, seems very high. 

The way that it fits to you also means it's extremely versatile where you can take it with you where you want to (you pick it up in 1 hand pretty easily) and you can use it in pretty much any exercise you like, including skill activities.

Limitless potential!

Pumped for footy being back tomorrow night too by the way!!!!

PSYCHOLOGICAL PROFILES OF ELITE ATHLETES STUDY

                                                               

These notes come from this study on elite Soccer players but the exact same information processing and decision making processes is required for footy.

• Sport at any level requires a deep understanding of the game, rapid information processing and decision making, not just physical abilities
• To close these gaps this study used elite soccer players and then focused on more psychological aspects of performance than other studies such as problem-solving, memory, executive functions and personality traits while evaluating via multiple means to get a comprehensive assessment
• Elite athletes demonstrated heightened planning/memory capacity, enhanced executive functions - especially cognitive flexibility - elevated levels of conscientiousness, extraversion and openness to experience, coupled with reduced neuroticism and agreeableness
• Non athletes report high elevated levels of neuroticism and agreeableness
• Executive functions (high order top-down regulatory mechanisms controlling low level processes) are of great importance for success in ball sports as they make it possible to adapt and plan behaviour in a fast-changing environment
• Design fluency performance correlates higher with national players then with Premier League players and those players are also described by coaches as the best readers in the game
• Executive function and coach-rated game intelligence also correlates highly
• The battery of tests they used were also able to predict assist/scoring behaviours + dribbling
• Versus the control group, soccer players have better memory, problem-solving skills, are better at planning tasks, have higher levels of working memory, have superior efficiency in analysing situations/devising optimal strategies to achieve their goals in the same time frame, have the ability to plan several steps ahead in order to reach a goal quickly in a changing environment, reach high scores on temperamental scales such as persistence, harm avoidance and cooperation while also score higher on impulsive scales such as seeking sensation and positive urgency
• Working memory is the single strongest correlator