Naked POC Magnetism Fill Probability & Median WaitNaked POC Magnetism — Fill Probability & Median Wait
What it is
A naked POC is the highest-volume price of a past session that price has not revisited since. Traders treat them as magnets — but "it usually gets filled" is folklore until it's measured. This tool measures it. Every historical naked level on your chart becomes a data point (how many sessions it survived before being touched, or whether it never was), and a survival model (discrete-hazard life table) turns that history into, for each live naked level: the probability it fills within the next N sessions and the median wait. Levels are drawn with their measured magnetism, not just their location.
How the statistics work — and their honest limits
Each session's volume-at-price profile is built from that session's bars; at session close the peak-volume price (POC) becomes a naked level.
A level is filled the first time a later bar's range touches it; its age in sessions at that moment is one observation. Levels removed unfilled (history cap) are censored at their age — counted as "survived this long," never as fills. This is the standard treatment of incomplete observations from survival analysis (Kaplan–Meier 1958; classical life tables).
Hazard at age j = fills at age j ÷ levels at risk at age j. Survival multiplies (1 − hazard) across ages; fill-probability within a horizon and the median wait follow directly.
Reliability gates, enforced not footnoted: no probability is displayed until a minimum number of levels have resolved (input, default 20) — until then the tool says BUILDING and shows only counts. And hazard estimates at ages with fewer than 5 at-risk observations are truncated rather than trusted, per standard life-table convention.
Probabilities are empirical frequencies from this symbol and timeframe's own history — they change with regime and sample, and a 70% is not a promise.
Seeing the evidence
Every historical fill prints a small ◈ marker where a naked level was touched — the resolved observations the probabilities are measured from, visible on the chart rather than hidden in a table.
The dashboard shows both the NEAREST level and the STRONGEST magnet (highest fill probability) — they are often not the same level, and the strongest one is the better answer to "where is price most drawn".
An honest design note: this tool deliberately has NO multi-timeframe stack and NO state-debounce, unlike its siblings in this suite — sessions are the model's clock regardless of chart timeframe (a higher-timeframe copy would measure the same sessions with coarser bins), and nothing here chatters (levels are born at session close and resolve on touch). Features are added where they inform, not everywhere.
How to use it
Add to a liquid intraday chart; 5m–15m gives the model the most sessions to learn from. Let it run until the dashboard reads MEASURED.
Each rail is labelled like "NPOC 24512 · 68% /5s · med 3s" — the measured chance it fills within the horizon and the median sessions historically needed. Warm, saturated rails = strong magnets; faded = weak or unrated.
The dashboard shows the nearest level's read and — deliberately — the sample size behind every number.
Use magnetism as context about where price is drawn (targets, fade zones, expectations management), never as an entry signal by itself.
What makes it original
Naked-POC indicators draw lines. This one attaches a measured fill-probability and expected wait to each line, estimated with a proper survival model that handles censoring and refuses to show numbers it can't support. Turning a folklore level into a level with a live, honest statistic is the contribution.
Concept credits
Market Profile / point of control — J. Peter Steidlmayer. Naked (virgin) POC — market-profile trading literature. Survival estimation from incomplete observations — E. L. Kaplan & P. Meier (1958); classical life-table method. Implementation and charting design are the author's own.
Important disclaimer
Research and education only. Not financial advice, not a signal service, not a guarantee of future results. Fill probabilities are empirical frequencies measured on this chart's limited history. Validate independently and manage your own risk. Indicator
Regime Transition Intelligence [AGPro Series]Regime Transition Intelligence
Most regime scripts answer a single question: "what regime are we in right now?". Regime Transition Intelligence is designed to answer a different, more actionable set of questions: how long does this regime usually last, how close to its typical end is it, how likely is it to flip within the next N bars, and where does it historically go when it does flip. Instead of treating the current regime as a standalone snapshot, it builds a living, self-calibrating statistical profile of the symbol's own regime behavior and presents it in a compact on-chart dashboard.
The engine runs on three independent axes — Trend Strength (Kaufman Efficiency Ratio + ADX), Chop Risk (Choppiness Index + inverse trend), and Volatility (ATR% normalized over a user-defined lookback). Each axis is classified as LOW / MID / HIGH, either with fixed 33/67 thresholds or with an adaptive percentile rank engine that learns the symbol's own statistical envelope over a rolling window. The three axes are then combined into a discrete regime state: TREND, MIXED, or RANGE / CHOP.
🟦 Overview / What it does
Regime Transition Intelligence is a single-pane overlay indicator that continuously classifies the market into one of three regimes and then layers a full transition intelligence stack on top of that classification:
- A per-regime dwell-time distribution learned from the chart's own completed regime blocks
- A Bayesian-style flip probability that answers "how likely is a regime change within the next N bars, given the current age"
- A 3x3 transition matrix that ranks the most likely next regime with a secondary fallback
- A fatigue score comparing the current regime's age to its historical mean (FRESH / MATURE / EXTENDED)
- A confidence decay tracker that shows whether conviction is BUILDING, STABLE, or FADING within the current regime block
- A compact history ribbon showing the last completed regime blocks with their durations
- Higher-timeframe alignment with a SYNC / DIV indicator and a live beacon at the right edge of the chart
All of this is delivered inside a single configurable dashboard, a directional transition marker layer on the chart, optional regime tint and candle coloring, and a right-edge beacon summarizing the current state.
🟣 Unique Edge / Why it is not a basic mashup
Standard regime indicators report the current state and stop there. Regime Transition Intelligence adds six distinct statistical layers that together form a transition-aware view:
1. Dwell Time Statistics — the script stores every completed regime block in a rolling array (configurable depth) and continuously updates running mean, running variance, running max, and running count per regime code. Statistics are only shown after a minimum number of blocks per regime have been collected, so the user always knows when the sample size is still too small.
2. Exponential Hazard Flip Probability — the baseline flip probability uses P(flip within H bars) = 1 - exp(-H / mean), a standard survival-analysis construction assuming constant hazard. The result is then fatigue-adjusted: if the current age is far above the historical mean, the probability is boosted; if the regime has just started, the probability is damped. The final value is capped at 95% to avoid certainty claims.
3. Transition Matrix — a 3x3 counter records every observed regime transition and is read as a conditional distribution: "given the current regime ends, which regime is it most likely to move to, and what is the runner-up". Both the top candidate and the secondary candidate are displayed with their percentages.
4. Fatigue Score — the ratio of the current age to the historical mean is bucketed into three zones (FRESH, MATURE, EXTENDED) using user-configurable thresholds. It tells the user whether the current regime is still in its early lifecycle or already past its typical end.
5. Confidence Decay Tracker — conviction in the current regime is sampled at the start of each new block and compared to the current conviction. The delta is classified as BUILDING, STABLE, or FADING, which gives an early read on whether the regime is strengthening or losing its grip.
6. History Ribbon — the last N completed regime blocks are compressed into a single compact line such as "C2·M4·C8·M1·M7*", where letters are regime codes and numbers are bar counts, with the current block marked by an asterisk. It gives immediate context on recent regime rhythm at a single glance.
None of these layers is a repackaged classic indicator. They are built on top of a trend / chop / volatility engine but deliver information that is categorically different from a simple "regime yes / no" readout.
🟢 Methodology / Conceptual data flow
1. Feature extraction. Kaufman Efficiency Ratio (net move over lookback divided by summed absolute moves) and normalized ADX are combined into a trend score. The Choppiness Index is normalized against its operating range and blended with inverse trend to produce a chop score. ATR as a percentage of price is normalized against its own lookback min/max to produce a volatility score.
2. Classification. Each score is mapped to LOW / MID / HIGH using either fixed thresholds (Static mode) or percentile rank over an adaptive lookback (Adaptive mode). The three bands are combined into a discrete regime state: TREND when trend is HIGH and chop is LOW, RANGE / CHOP when chop is HIGH, and MIXED otherwise.
3. Block tracking. Every time the regime state changes on a confirmed bar, the previous block is closed: its duration is pushed to a rolling history array and added to the running sum / sum-of-squares / count / max for its regime code. When the history array exceeds its configured depth, the oldest block is popped and its contribution is subtracted from the running totals, which keeps the statistics adaptive and non-expanding.
4. Transition matrix update. When a block closes into a new regime, the 3x3 counter is incremented at the corresponding cell, and the row total is incremented. The conditional distribution for the current regime is read from its row at display time.
5. Statistical outputs. Mean dwell, fatigue ratio, exponential-hazard flip probability, fatigue-adjusted flip probability, top and secondary next regimes, and confidence delta are all derived from the running state and rendered into the dashboard.
6. Higher-timeframe alignment. The same three-axis engine is run on a user-selected higher timeframe via request.security and compared against the current-timeframe regime; the result appears as SYNC or DIV in the header and as an optional HTF row in the dashboard.
🔔 Signals & Alerts / Interpretation
Regime Transition Intelligence is a state-mapping and statistical context tool rather than a directional buy / sell engine. The main on-chart events are:
- Regime Shift — fires when the regime state changes on a confirmed bar
- High Flip Probability — fires when the fatigue-adjusted flip probability crosses a high threshold
- Regime Fatigue Extended — fires on the transition into the EXTENDED fatigue zone
- Confidence Fading — fires on the transition into the FADING confidence zone
How to read the panel:
- Summary + Age tells the user which regime is active and how long it has been active.
- Dwell Context compares the current age to the historical mean in the form "age / mean · % of typical lifespan".
- Fatigue summarizes that comparison as FRESH, MATURE, or EXTENDED.
- Flip Probability reports the statistical odds of a regime change within the user-defined horizon.
- Next Likely names the most probable next regime with its percentage and a secondary fallback.
- Confidence and Conf Decay together tell the user whether the current read is reliable and whether conviction is rising or fading.
- History gives quick situational awareness of recent regime rhythm.
None of these rows should be interpreted as a trade instruction. They are a context layer meant to be combined with the user's own structure and entry framework.
🎛️ Key Inputs
Regime Engine Core — Trend Persistence Length, DMI/ADX Length, Chop Length, ATR Length, Volatility Normalize Lookback.
Adaptive Boundaries — Band Classification Mode (Adaptive / Static), Adaptive Lookback, Adaptive Low / High Percentile.
Transition Intelligence — Regime History Depth, Flip Probability Horizon, Min Blocks Before Stats Activate, Fatigue Fresh / Extended thresholds.
HUD — Display Mode (PRO / MINIMAL), HUD Position, Text Size, transparency controls, individual row toggles, history ribbon length.
Add-ons — Chart Regime Tint, Regime Candle Coloring (Soft / Strong), HTF Peek Timeframe, Transition Markers (location, cooldown, stagger, size, ATR offset), Live Regime Beacon (position, size, stats toggle).
🧭 How to use
1. Add the script to any chart and timeframe. The engine is tuned to work from 15m up to Daily; very low timeframes on illiquid instruments can produce unstable regime blocks and are not the intended use case.
2. Give the script time to collect blocks. Statistics stay in N/A until the configured minimum number of completed blocks per regime has accumulated. On a fresh chart or an illiquid instrument this is expected behavior, not a bug.
3. Read the dashboard top-down. Start with the three axis rows to understand the current market shape, then move to Summary and Age to see what is active and for how long, then use Dwell / Fatigue / Flip / Next Likely to place the current regime inside its historical distribution, and finally use Conf Decay and HTF to sanity-check reliability and alignment.
4. Treat EXTENDED fatigue and high flip probability as context, not as a reversal signal. Regimes can remain in the EXTENDED zone for a while before actually flipping; the statistical profile is descriptive, not deterministic.
5. Combine with structural context. The script does not know about support / resistance, order blocks, or news. It only knows about the symbol's own regime rhythm. Use it as a regime-aware filter on top of the user's existing framework.
⚠️ Limitations & Transparency
This is not a strategy and not a complete trading system. It does not predict price direction and does not generate buy or sell signals. All statistics are estimated from a rolling history of the chart's own regime blocks, so they are sensitive to the chosen engine parameters, the timeframe, and the symbol; different timeframes and different instruments will produce different statistical profiles, and that is by design.
The exponential-hazard flip probability assumes a constant hazard within the current regime, which is a simplification. Real-world regime durations are not perfectly memoryless and the fatigue multiplier is a heuristic correction, not a formal model. The probability is capped at 95% on purpose, because even a heavily aged regime cannot be considered a certainty and the script deliberately avoids certainty language.
The transition matrix is read as a conditional frequency over completed blocks; it is informative about the symbol's own past behavior and should not be interpreted as a forward-looking forecast. Very small samples produce unstable conditional probabilities, which is why stats stay in N/A until a minimum number of blocks is collected.
Regime classification itself reacts to confirmed bars and can change as new data arrives, which is expected for any regime filter. Users who prefer fully non-repainting alerts should rely on the barstate.isconfirmed-gated alert conditions provided.
📜 Risk Disclosure
Trading involves substantial risk of loss and is not suitable for every investor. Past performance is not indicative of future results. This indicator is provided for educational and analytical purposes only and should not be interpreted as financial advice, an investment recommendation or a solicitation to trade. Always combine multiple forms of analysis, manage position size responsibly, and never risk capital you cannot afford to lose. Indicator
Level Survival Map [AGPro Series]Level Survival Map
🔹 Overview
Level Survival Map is a premium support and resistance framework that does not just draw lines on the chart. Every detected level carries a live Survival Score between 0 and 100 that answers one simple question: how well is this level still defending itself right now. The map highlights a single Active Level with an interaction zone and a forward projection ribbon, while nearby weaker levels fade, so traders always know which level actually matters for the current decision.
🔸 Unique Edge
Most support and resistance tools either show static pivots or basic break or retest events. Level Survival Map goes further by measuring the quality of every interaction and turning it into a single composite health score per level. Instead of being left with a wall of equally important lines, the trader sees a ranked structural battlefield with one clearly identified Active Level, a visible interaction zone and a projection ribbon for planning. The Damage State readout, the Fresh and Eroded state semantics, the automatic flip from broken support to new resistance and the cluster fade for crowded weaker levels are designed to work together as one premium, low-noise workflow.
🔹 Methodology
Pivot detection builds the raw candidate levels from swing highs and swing lows using the standard pivot window. A merge filter removes duplicates that sit within a configurable ATR distance of an existing same-type level. Each active level then accumulates four independent components over time. Close Respect rewards closes that respect the level side, for example closes above a support. Penetration Damage penalises wicks and bodies that pierce through the level zone. Reaction Quality rewards strong rejection wicks and bodies moving away from the level after a test. Test Fatigue penalises repeated tests because levels tend to weaken with each new hit. These four components are weighted and combined into a single Survival Score, then clamped between 0 and 100. A structural break caps the score at 35, heavy damage across multiple tests caps it at 28, and a confirmed sequence of opposite-side closes flips the level type while resetting its history. The Active Level is chosen as the closest same-side level to price so that the focus always follows the real decision point.
🔸 Signals and Alerts
The visual output itself is the primary signal. Line colour and thickness communicate level strength at a glance. A focused Active Level is drawn with an interaction zone, a darker core band and a forward projection ribbon so that traders can see the exact price band where reaction is most likely, and how far into the future that band is expected to remain relevant. Labels carry the Survival Score directly, so the ranking of levels is always visible without opening any settings. Broken levels switch to a dashed style and faded colour, and once enough opposite-side closes accumulate they flip type automatically, giving a clear visual signature of structural change.
🔹 Key Inputs
Pivot Left Bars and Pivot Right Bars control how strict the swing detection is. Max Active Levels caps how many concurrent levels are tracked. Level Merge Distance and Interaction Zone are expressed in ATR units so the logic adapts across timeframes and instruments. Scoring weights for Close Respect, Penetration Damage, Reaction Quality and Test Fatigue can be tuned independently, together with the fatigue penalty per extra test and the number of closes required to confirm a flip. Visual inputs cover panel position, label size, line width, focus emphasis, non-focus transparency, cluster fade, focus zone width and projection ribbon length and thickness. A Clean Map Mode is provided for screenshot and publishing workflows where only the Active Level and the nearest valid support and resistance are labelled.
🔸 How to Use
Read the map top down. First, look at the summary panel for the Active Level, its Survival Score, Test Count and Damage State. A Fresh or Strong Active Level defending its side is a high-quality decision point. A Fragile or Eroded Active Level with a Severe Damage State is a warning that the next level below or above is likely to take over. Use the projection ribbon as a planning band for reaction rather than a mechanical entry. Use the ranked non-Active labels to understand where price is likely to travel if the Active Level gives way. The tool is designed to be used as a visual framework, in combination with the trader own execution method, trend context and risk management.
🔹 Limitations and Transparency
This indicator is a visual analytical framework, not a strategy, not a signal service and not financial advice. Survival Score, Damage State and flip logic are deterministic functions of price action and ATR, so different markets and timeframes will produce different characteristic score ranges. Pivot based detection is inherently lagging by the Pivot Right Bars window, which is the expected behaviour of any structural tool and not a defect. The Active Level projection ribbon is a visual planning aid, not a forecast. Past level behaviour does not guarantee future behaviour.
🔸 Risk Disclosure
Trading involves substantial risk and is not suitable for every investor. This script is published for educational and analytical purposes only. Users are solely responsible for their own trading decisions, position sizing and risk management. Always test any tool on your own instruments and timeframes before using it in a live environment. Indicator
FunctionSurvivalEstimationLibrary "FunctionSurvivalEstimation"
The Survival Estimation function, also known as Kaplan-Meier estimation or product-limit method, is a statistical technique used to estimate the survival probability of an individual over time. It's commonly used in medical research and epidemiology to analyze the survival rates of patients with different treatments, diseases, or risk factors.
What does it do?
The Survival Estimation function takes into account censored observations (i.e., individuals who are still alive at a certain point) and calculates the probability that an individual will survive beyond a specific time period. It's particularly useful when dealing with right-censoring, where some subjects are lost to follow-up or have not experienced the event of interest by the end of the study.
Interpretation
The Survival Estimation function provides a plot of the estimated survival probability over time, which can be used to:
1. Compare survival rates between different groups (e.g., treatment arms)
2. Identify patterns in the data that may indicate differences in mortality or disease progression
3. Make predictions about future outcomes based on historical data
4. In a trading context it may be used to ascertain the survival ratios of trading under specific conditions.
Reference:
www.global-developments.org
"Beyond GDP" ~ www.aeaweb.org
en.wikipedia.org
www.kdnuggets.com
survival_probability(alive_at_age, initial_alive)
Kaplan-Meier Survival Estimator.
Parameters:
alive_at_age (int) : The number of subjects still alive at a age.
initial_alive (int) : The Total number of initial subjects.
Returns: The probability that a subject lives longer than a certain age.
utility(c, l)
Captures the utility value from consumption and leisure.
Parameters:
c (float) : Consumption.
l (float) : Leisure.
Returns: Utility value from consumption and leisure.
welfare_utility(age, b, u, s)
Calculate the welfare utility value based age, basic needs and social interaction.
Parameters:
age (int) : Age of the subject.
b (float) : Value representing basic needs (food, shelter..).
u (float) : Value representing overall well-being and happiness.
s (float) : Value representing social interaction and connection with others.
Returns: Welfare utility value.
expected_lifetime_welfare(beta, consumption, leisure, alive_data, expectation)
Calculates the expected lifetime welfare of an individual based on their consumption, leisure, and survival probability over time.
Parameters:
beta (float) : Discount factor.
consumption (array) : List of consumption values at each step of the subjects life.
leisure (array) : List of leisure values at each step of the subjects life.
alive_data (array) : List of subjects alive at each age, the first element is the total or initial number of subjects.
expectation (float) : Optional, `defaut=1.0`. Expectation or weight given to this calculation.
Returns: Expected lifetime welfare value. Library
Strategy
