• Composer • Artistic Director • AI/ML Developer • Quantitative Researcher
AMIN SHARIFI
• Composer • Artistic Director
• AI/ML Developer • Quantitative Researcher
Developing Frameworks of Algo-Rhythm​
From Music to Markets:
An Interdisciplinary Journey
Amin Sharifi is a composer, AI and machine learning systems developer, and quantitative researcher whose work bridges contemporary classical music, advanced algorithmic trading systems, and interdisciplinary research. His career is driven by a fascination with patterns, systems, and complexity, whether expressed in the mathematical structures of his compositions or the data-driven models powering his trading strategies. Read more
QuantRL: Deep Reinforcement Learning System for Algorithmic Trading
QuantRL is a modular, research-grade reinforcement learning (RL) framework designed to model, train, and evaluate AI-based trading agents in a realistic financial environment. It is built around the Proximal Policy Optimization (PPO) algorithm using a custom self-attention neural network architecture and incorporates feature-rich market simulation, advanced backtesting, and performance evaluation.
​
PARAMETRIC MUSIC
Amin Sharifi’s compositional practice treats music as a formally specified system in which materials are generated, transformed, and perceived through explicit constraints. He works with graphic notation as a primary medium, using visual grammars that encode temporal, gestural, and textural information so that the score functions both as executable instruction and as autonomous visual artifact. This emphasis on notation as a designed interface allows him to address the composer–performer–listener triad with traceable rules rather than opaque virtuosity, a stance that converses with New Complexity performance practice while redirecting it toward legible, information-rich surfaces. Parametric control of rhythm, articulation, and timbre is expressed in families of symbols whose semantics are fixed before sound, which situates the work within a lineage that includes intricate notational ecologies and high-density structural thinking. In this frame, the score is not a picture of music but a compiled program for behavior, extending the tradition of complex notation and graphic scores into a coherent, rule-driven design language.
​
SPECTRAL MORPHOLOGY
Sharifi’s musical materials are derived and organized by quantitative methods that privilege pattern discovery and structural inference. He employs spectral analysis to derive pitch and timbral fields, uses perceptual and morphological segmentation logics akin to novelty and change-point detection for form articulation, and designs temporal fabrics with simultaneous, non-integer tempo relationships that behave like tempo canons. Architectural mappings translate geometric primitives into continuous trajectories, so that glissandi, density envelopes, and registral vectors realize graphical or algebraic constructions in sound. The resulting works read as multi-scale systems in which local constraints propagate to global form, and where visual topology, algorithmic formalism, and listening thresholds cohere into a single specification of behavior. This approach aligns with precedents that link mathematical structure to musical outcome, including Xenakis’s transfers between geometric design and orchestral glissandi, and scholarship on the analysis and composition of multiple concurrent tempos, while adopting contemporary MIR-style tools to ensure that section boundaries and textural pivots are audibly inferable.
APOSYNTHESY
In "Aposynthesy" ("Decomposition") my tribute to Meshkatian and his evocative composition, I dissect and reassign value to every frequency from the original recording, meticulously quantizing each frequency series to its closest pitch. The temporal essence of the original frequencies is preserved, albeit transformed, by quantizing milliseconds to the nearest 32nd rhythm and applying dynamic stretching and compression. This method distorts yet venerates the original, filtering it through multiple layers of auditory transformation to offer a unique, multi-dimensional perspective on a classic piece.