</> Codebase

The Kalman Filter is a mathematical approach often used in engineering and finance to produce smooth, adaptive estimates of a system’s state—in this case, the price of a financial instrument. By combining past estimates and new measurements, the Kalman Filter helps reduce noise and track both the price and its velocity (or slope) over time.

The Ultimate Oscillator is a technical analysis tool designed to capture momentum by combining three different time periods into a single value. By weighing short-term, mid-term, and long-term price pressures, it aims to minimize false signals that can arise from focusing on any single timeframe.

In our latest update, we've introduced new comparison blocks that allow you to smooth any indicator using various moving averages, such as SMA, EMA, WMA, or HMA. These blocks enable you to compare an indicator's current value to its smoothed version, helping to filter out market noise and focus on significant trends. You can specify parameters like the period, moving average type, and shift to tailor the smoothing to your strategy. This enhancement provides traders with refined tools to develop more robust and responsive trading strategies.

CUSUM is a sequential analysis technique that accumulates deviations from a target value over time. By comparing the cumulative sum against defined thresholds, it becomes easier to spot even subtle shifts in price behavior. In our implementation, two separate accumulators—one for upward movements (CUSUM Positive) and one for downward movements (CUSUM Negative)—signal when the change in the underlying price series becomes significant.

These custom blocks, or conditions, were used in the analysis of the effectiveness of more adaptive blocks, which you can read here. Additionally, these custom blocks can serve as a template for you to prepare your own.

The Kolmogorov-Smirnov Test (KSTest) indicator is a statistical tool used in quantitative trading to compare two data samples and determine if they come from the same distribution. In this implementation, the indicator compares a recent sample of price data ( Period1) with a historical sample (Period2) to detect significant changes in the underlying distribution of the data.

The IsGreater Is/Lower Adaptive comparison block does one main thing: it checks if one indicator is greater than another, but only generates a signal if similar situations were profitable in the past.

Autocorrelation measures the degree of similarity between a time series and a lagged version of itself. Simply put, it determines if today’s price movements relate to movements from a specific number of periods ago.

I modified the original Stagnation code to use an average stagnation (daily basis) as the metric, for 2 reasons: 1. To know on average how many days before a new

Adaptive blocks “Crosses Above/Below Adaptive” bring a new level of intelligence to trading strategies by incorporating historical signal performance. Unlike standard blocks that only detect when one indicator crosses another, adaptive blocks analyze how similar signals performed in the past to estimate the reliability of the current signal.