The standard addition method is widely used in analytical chemistry to compensate for matrix effects. While effective with single signals (e.g., absorbance at a single wavelength) and independent of matrix composition or blank measurements, it has limitations with high-dimensional data (e.g., full spectra). Existing methods for high-dimensional data require knowledge of the matrix composition and blank measurements, restricting their applicability. We propose a novel algorithm for standard addition that works with high-dimensional data without requiring matrix composition knowledge or blank measurements. By modifying experimental data (e.g., spectra) before applying chemometric models, the algorithm accurately determines analyte concentrations even in complex matrices like seawater or food, where blanks are unavailable. A performance evaluation shows the algorithm compensates effectively for matrix effects, outperforms previously published standard addition algorithms and direct applications of multivariate chemometric algorithms, and is robust to variations in SNR and matrix effect intensity.