Ai Portfolio Optimization | AI Final Year Project Report

Complete Technical Paper Content — Ai Portfolio Optimization

1. Executive Abstract, Problem Formulation & Background

An AI agent, also known as agentic AI, is an artificial intelligence program that can make decisions, pursue goals, and take actions independently of human programmers. Agentic AI contrasts with tool-like AI use for narrow, specific tasks such as answering questions, as with chatbots in the non-agentic forms that were common since 2023, or with traditional machine learning algorithms. While there is no universally agreed-upon definition of an AI agent, common attributes of AI agents include goal-directed behavior, use of external tools, the ability to interact with and modify an external environment, and the ability to autonomously perform multi-step tasks. Their control flow is frequently driven by large language models (LLMs). Agent systems may also include memory components, planning logic, tool interfaces, and orchestration software for coordinating agent components.

The theoretical underpinnings for artificial agents emerged in the mid 20th century, with establishment of cybernetics and artificial intelligence. Oliver Selfridge's 1958 "Pandemonium: A Paradigm for Learning" paper was an important early theoretical contribution in establishing agent oriented architecture. Practical implementations of agents for real world applications began to become widespread in the 1990s, after the introduction of the belief–desire–intention software model (BDI), and agent-oriented programming. Harvard professor Milind Tambe notes that in the 1990s, the definition of an AI agent was not clear. Pure digital agents were deployed in computer infrastructure for purposes such as monitoring, while agents connected to real-world sensors and actuators were increasingly used in industrial control systems. Early artificial agents tended to have simple if then logic, which expanded over time into large decision tree models. By the early 2010s, products like Siri and Alexa were released, and were sometimes called AI agents, though they lacked the general purpose reasoning ability of later agents run by large language models (LLMs). The development of LLMs during the late 2010s and early 2020s introduced new approaches to AI agents. Models such as GPT-3 demonstrated the ability to generate and understand natural language at a much larger scale than many earlier language systems. Academics began to study LLM agents from 2018. Deployment of such agents began to accelerate in late 2023 after OpenAI's "function-calling" API was made available, and especially after Anthropic's late 2024 introduction of Model Context Protocol (MCP), a standardised way for LLM agents to gain contextual awareness, and to act on the world by calling various external tools. The term "agentic" only began to be used with any frequency in 2024, popularised in part by researcher Andrew Ng.

Ken Huang proposed an AI agent reference architecture that consists of seven interconnected layers, with each layer building on the functionality of the layers beneath it:

Layer 1: Foundation models – provide the datasets that power the agent. Layer 2: Data operations – manages the data infrastructure required for AI agent operations, including vector databases, data loaders, and RAG. Layer 3: Agent frameworks – software that manages the AI agents. Layer 4: Deployment and infrastructure – the technical foundation of the AI agents. Layer 5: Evaluation and observability – the safety and performance of AI agents. Layer 6: Security and compliance – a protective framework for safe operation and compliance with regulatory boundaries. At this layer, security and compliance features embedded into all the AI agent stack layers are integrated together. Layer 7: Agent ecosystem – represents the AI agents' interface with real-world applications and users.

An agent harness, or agent scaffold, is the software layer surrounding a large language model that enables it to function as an AI agent. It commonly manages prompts, context, tool use, memory, execution state, operational constraints, sandboxes, permissions, and the processing of results. The harness connects the model to internal and external computer hardware, software, data files, databases, web browsers, command-line interfaces, and application programming interfaces, while controlling how the agent accesses and uses these resources to complete multi-step tasks.

Prompt chaining: A sequence where the output of one step serves as the input for the next. Routing: Directing an input to a specialized downstream task or tool. Parallelization: The simultaneous execution of multiple tasks. Sequential processing: A fixed, linear progression of tasks through a predefined pipeline. Planner-critic: An iterative pattern where one agent generates a proposal and another evaluates it to provide feedback for refinement.

STRIDE: A Microsoft model that identifies threats across six categories: spoofing, tampering, repudiation, information disclosure, denial of service, and elevation of privilege. MITRE ATLAS: A knowledge base of adversary tactics and techniques for AI systems. OWASP GenAI Security Project: Provides guidance on vulnerabilities associated with generative AI and large language model integration, including guidelines specifically for agentic applications. MAESTRO: A framework from the Cloud Security Alliance for assessing risks in AI systems throughout their lifecycle.

Artificial intelligence (AI) and its subfields have been used in applications throughout industry and academia. Machine learning has been used for various scientific and commercial purposes, including language translation, image recognition, decision-making, credit scoring, and e-commerce. Since the 2020s, massive advancements have been made in the field of generative AI (GenAI) as a result of the 2017 inception of Transformer Model architecture. GenAI has the ability to create text, images, voice, music, videos, and other forms of data from chat-based prompting.

In agriculture, AI has been proposed as a way for farmers to identify areas that need irrigation, fertilization, or pesticide treatments to increase yields, thereby improving efficiency. AI has been used to attempt to classify livestock pig call emotions, automate greenhouses, detect diseases and pests, and optimize irrigation.

2. Related Work, Literature Survey & Algorithmic Foundations

A 2019 study found that generative AI increased productivity by 15% in contact centers. Another 2019 study found it increased productivity by up to 40% for writing tasks. An August 2025 review by MIT found that of surveyed companies, 95% did not report any improvement in revenue from the use of AI. In September 2025, a Harvard Business Review article described how increased use of AI does not automatically lead to increases in revenue or actual productivity. Referring to "AI generated work content that masquerades as good work, but lacks the substance to meaningfully advance a given task", the article coined the term workslop. Per studies done in collaboration with the Stanford Social Media Lab, workslop does not improve productivity and undermines trust and collaboration among colleagues. In telehealth, agentic AI is reportedly facilitating the creation of large business models (millions in annual profit) with 1–2 employees, such as MEDVi, which as of August 2025 only had 2 employees and ~$75M in annual profit for GLP-1 weight-loss telehealth services.

Research and development of quantum computers has been performed with machine learning algorithms. For example, there is a prototype, photonic, quantum memristive device for neuromorphic computers (NC)/artificial neural networks and NC-using quantum materials with some variety of potential neuromorphic computing-related applications. The use of quantum machine learning for quantum simulators has been proposed for solving physics and chemistry problems.

Artificial intelligence and machine learning are used in electronic design automation to assist with integrated circuit design, including floorplanning, placement, routing, functional verification, and optimization of power, performance, and chip area.

Time sharing Interactive interpreters Graphical user interfaces and the computer mouse Rapid application development environments The linked list data structure Automatic storage management Symbolic programming Functional programming Dynamic programming Object-oriented programming Optical character recognition Constraint satisfaction

AI programs have been used in hiring processes to screen resumes and rank candidates based on their qualifications, predict a candidate's likelihood of success in a given role, and automate repetitive communication tasks using chatbots. Studies on these programs have identified tendencies for gender bias, favoring male names and male-coded characteristics, as well as bias against disabled candidates and racial minorities.

AI underlies avatars (automated online assistants) on web pages. It can reduce operation and training costs. In 2016, Pypestream automated customer service for its mobile application to streamline communication with customers. A Google app analyzes language and converts speech into text. The platform can identify angry customers through their language and respond appropriately. Amazon uses a chatbot for customer service that can perform tasks like checking the status of an order, cancelling orders, offering refunds, and connecting the customer with a human representative.

In educational institutions, AI has been used to automate routine tasks such as attendance tracking, grading, and marking. AI tools have also been used to monitor student progress and analyze learning behaviors, with the goal of facilitating timely interventions for students facing academic challenges. As of 2025 and 2026, respectively, about 80% of high school students and nearly 60% of college students were also using AI. Some schools and universities proposed restrictions on students' usage due to issues with increased cheating, over-reliance on AI tools, and widening of digital inequities.

The U.S. Department of Energy wrote in an April 2024 report that AI may have applications in modeling power grids, reviewing federal permits with large language models (LLMs), predicting levels of renewable energy production, and improving the planning process for electrical vehicle charging networks. Other studies have suggested that machine learning can be used for energy consumption prediction and scheduling (e.g., to help with renewable energy intermittency management).

The late 1980s and early 1990s saw expert systems used in technical and environmental domains. For example, researchers built a fishway design advisor to recommend fish passage structures under varying hydraulic and biological conditions using the VP-Expert shell. Transportation researchers applied the same shell to balance airport capacity with noise-mitigation plans. In agriculture, a potato insect expert system (PIES) supported pest management decisions for Colorado potato beetle. The U.S. Environmental Protection Agency's CORMIX system for modeling pollutant discharges combined rules with Fortran hydrodynamic models. Autonomous ships that monitor the ocean, AI-driven satellite data analysis, passive acoustics or remote sensing and other applications of environmental monitoring make use of machine learning. For example, "Global Plastic Watch" is an AI-based satellite-monitoring platform for analysis/tracking of plastic waste sites to help with the prevention of plastic pollution—primarily ocean pollution—by helping identify who mismanages plastic waste and where dumping into oceans occurs.

3. Dataset Ingestion, Preprocessing & Stochastic Augmentations

AI applications analyze media content such as movies, TV programs, advertisement videos, and user-generated content. The solutions often involve computer vision. Typical scenarios include the analysis of images using object recognition or facial recognition techniques, or the analysis of video for recognizing scenes, objects, or faces. AI-based media analysis can facilitate media search, the creation of descriptive keywords for content, content policy monitoring (such as verifying the suitability of content for a particular TV viewing time), speech to text for archival or other purposes, and the detection of logos, products, or celebrity faces for ad placement.

Motion interpolation Pixel-art scaling algorithms Image scaling Image restoration Photo colorization Film restoration and video upscaling Photo tagging Text-to-image models (such as DALL-E, Midjourney, and Stable Diffusion) Image to video Text to video (such as Make-A-Video from Meta, Imagen video and Phenaki from Google) Text to music with AI models (such as MusicLM) Text to speech (such as ElevenLabs and 15.ai) Motion capture

AI has been used to compose music of various genres. David Cope created an AI called Emily Howell that became well known in the field of algorithmic computer music. The algorithm behind Emily Howell is registered as a US patent. In 2012, AI Iamus created the first complete classical album. AIVA (Artificial Intelligence Virtual Artist), composes symphonic music, mainly classical music for film scores. It became the first virtual composer to be recognized by a musical professional association. Melomics creates computer-generated music for stress and pain relief. The Watson Beat uses reinforcement learning and deep belief networks to compose music on a simple seed input melody and a select style. The software was open sourced, and musicians such as Taryn Southern collaborated with the project. South Korean singer Hayeon's debut song, "Eyes on You", was composed using AI which was supervised by real composers, including NUVO.

Narrative Science sells computer-generated news and reports. It summarizes sporting events based on statistical data from a game. It also creates financial reports and real estate analyses. Automated Insights generates personalized recaps and previews for Yahoo Sports Fantasy Football. Yseop uses AI to turn structured data into natural language comments and recommendations. It writes financial reports, executive summaries, and personalized sales or marketing documents in multiple languages, including English, Spanish, French, and German. TALESPIN made up stories similar to the fables of Aesop. The program started with a set of characters who wanted to achieve certain goals. Mark Riedl and Vadim Bulitko asserted that the essence of storytelling was experience management, or "how to balance the need for a coherent story progression with user agency, which is often at odds". While AI storytelling focuses on story generation (character and plot), story communication also received attention. In 2002, researchers developed an architectural framework for narrative prose generation. They faithfully reproduced text variety and complexity on stories such as Little Red Riding Hood. In 2016, a Japanese AI co-wrote a short story and almost won a literary prize. South Korean company Hanteo Global uses a journalism bot to write articles. Literary authors are also exploring uses of AI. An example is David Jhave Johnston's work ReRites (2017–2019), where the poet created a daily rite of editing the poetic output of a neural network to create a series of performances and publications.

In video games, AI is routinely used to generate behavior in non-player characters (NPCs). In addition, AI is used for pathfinding. Games with less typical AI include the AI director of Left 4 Dead (2008) and the neuroevolutionary training of platoons in Supreme Commander 2 (2010). In the 21st century, AIs have beaten human players in many games, including chess (Deep Blue), Jeopardy! (Watson), Go (AlphaGo), poker (Pluribus and Cepheus), E-sports (StarCraft), and general game playing (AlphaZero and MuZero). Kuki AI is a set of chatbots and other apps which were designed for entertainment and as a marketing tool.

The first AI art program, AARON, was developed by Harold Cohen in 1968 with the goal of being able to code the act of drawing. It started by creating simple black and white drawings, and later to painting using special brushes and dyes chosen by the program without mediation from Cohen. AI platforms such as DALL-E, Stable Diffusion, Imagen, and Midjourney have been used for generating visual images from inputs such as text or other images. Some AI tools allow users to input images and output changed versions, such as to display an object or product in different environments. AI image models can also attempt to replicate the specific styles of artists, and can add visual complexity to rough sketches. AI has been used to generate quantitative analysis of existing digital art collections. Two computational methods, close reading and distant viewing, are typical approaches used to analyze digitized art. While distant viewing includes the analysis of large collections, close reading involves one piece of artwork.

Banks use AI to organize operations for bookkeeping, investing in stocks, and managing properties. AI can adapt to changes during non-business hours.

The use of AI in applications such as online trading and decision-making has changed major economic theories. For example, AI-based buying and selling platforms estimate personalized demand and supply curves, thus enabling individualized pricing. AI systems reduce information asymmetry in the market and thus make markets more efficient. The application of AI in the financial industry can help alleviate financing constraints of non-state-owned enterprises, especially for smaller and more innovative enterprises. Large financial institutions use AI to assist with their investment practices. BlackRock's AI engine, Aladdin, is used both within the company and by clients to help with investment decisions. Its functions include the use of natural language processing to analyze text such as news, broker reports, and social media feeds. It then gauges the sentiment on the companies mentioned and assigns a score. Banks such as UBS and Deutsche Bank use SQREEM (Sequential Quantum Reduction and Extraction Model) to mine data to develop consumer profiles and match them with wealth management products.

AI in healthcare is often used for classification, such as to evaluate a CT scan or electrocardiogram or to identify high-risk patients for population health. Additional potential applications like robot-assisted surgery, virtual nursing assistants, and dosage error reductions could create billions in annual savings for U.S. health care. For certain disorders and diseases, AI algorithms can aid in diagnosis, recommended treatments, outcome prediction, and patient progress tracking. Early detection of diseases like cancer is made possible by AI algorithms, which diagnose diseases by analyzing complex sets of medical data. For example, Microsoft's AI project Hanover helps doctors choose cancer treatments from among the more than 800 medicines and vaccines. Studies have shown AI capable of identifying skin cancers and diagnosing eye conditions, similar to an ophthalmologist, and recommending treatment referrals via transfer learning. Another project monitors multiple high-risk patients by asking each patient questions based on data acquired from doctor/patient interactions. Artificial neural networks are used as clinical decision support systems for medical diagnosis, such as in concept processing technology in electronic medical record (EMR) software. Other healthcare tasks thought suitable for an AI that are in development include:

4. Neural Network Backbone, Layer Specifications & Loss Formulations

Screening Companion robots for elder care Drug creation (e.g. by identifying candidate drugs and by using existing drug screening data such as in life extension research) Clinical training Identifying genomic pathogen signatures of novel pathogens or identifying pathogens via physics-based fingerprints (including pandemic pathogens) Helping link genes to their functions, otherwise analyzing genes and identification of novel biological targets Help development of biomarkers Help tailor therapies to individuals in personalized medicine/precision medicine

AI-enabled chatbots decrease the need for humans to perform basic call center tasks, and machine learning in sentiment analysis can spot fatigue to prevent overwork. Decision support systems can potentially prevent industrial disasters and make disaster response more efficient. For manual workers in material handling, predictive analytics has been proposed to reduce musculoskeletal injury. AI can attempt to process workers' compensation claims. AI has been proposed for detection of accident near misses, which are underreported.

Speech translation technology attempts to convert one language into another. This could potentially reduce language barriers in global commerce and cross-cultural exchange, enabling speakers of various languages to communicate. AI has been used to automatically translate spoken language and textual content in products like Microsoft Translator, Google Translate, and DeepL Translator. Also, research and development are in progress to decode and conduct animal communication. Meaning is conveyed not only by text, but also through usage and context (see semantics and pragmatics). As a result, the two primary categorization approaches for machine translations are statistical machine translation (SMT) and neural machine translations (NMTs). The old method of performing translation was to use statistical methodology to forecast the best probable output with specific algorithms. However, with NMT, the approach employs dynamic algorithms to achieve better translations based on context.

AI facial recognition systems are used for mass surveillance, notably in China. In 2019, Bengaluru, India deployed AI-managed traffic signals that uses cameras to monitor traffic density and adjust signal timing based on the interval needed to clear traffic.

In the 1990s, early AI tools controlled toys like Aibo, a domestic robot in the form of a robotic dog with intelligent features and autonomy. In the mid-2010s, Mattel's Hello Barbie could "understand" conversations, give intelligent responses, and remember. AI in toys could offer personalized learning. However, in May 2026, after early tests to see how toddlers interact with AI, researchers called for tighter regulation on AI-powered toys. Similarly, nonprofit organization Common Sense Media warned against children under five using AI.

AI tools have been used to translate mathematical proofs into formal proofs to automatically verify them.

AI systems have also been used to search for improved algorithms and computational routines. AlphaTensor, AlphaDev, and AlphaEvolve have been applied to matrix multiplication algorithms, sorting routines, and broader scientific and algorithmic discovery.

Various countries are deploying AI military applications. Research is targeting intelligence collection and analysis, logistics, cyber operations, information operations, and semiautonomous and autonomous vehicles. AI has been used in military operations in Iraq, Syria, Israel, and Ukraine.

AI is used in robotics to help robots perceive their surroundings, plan actions, navigate, manipulate objects, and adapt to changing environments. AI systems are used to connect sensor data with physical action, especially in systems operating outside controlled factory settings.

5. Training Protocol, Convergence Behavior & Experimental Evaluation

Intelligent personal assistants use AI to attempt to respond to natural language requests. Siri, released in 2010 for Apple smartphones, popularized the concept. Bing Chat has used AI as part of its search engine.

Machine learning can be used to combat spam, scams, and phishing. It can scrutinize the content of spam and phishing attacks to attempt to identify malicious elements. Some models built via machine learning algorithms have over 90% accuracy in distinguishing between spam and legitimate emails. These models can be refined using new data and evolving spam tactics. Machine learning also analyzes traits such as sender behavior, email header information, and attachment types, potentially enhancing spam detection.

AI has been used in facial recognition systems. Some examples are Apple's Face ID and Android's Face Unlock, which are used to secure mobile devices. China has used facial recognition and AI technology in Xinjiang. In 2017, reporters visiting the region found surveillance cameras installed every hundred meters or so in several cities, as well as facial recognition checkpoints at areas like gas stations, shopping centers, and mosque entrances. Human rights groups have criticized the Chinese government for using AI facial recognition technology for use in political suppression. The Netherlands has deployed facial recognition and AI technology since 2016. As of 2019, the database of the Dutch police contained over 2.2M pictures of 1.3M Dutch citizens. This accounts for about 8% of the population. In The Netherlands, face recognition is not used by the police on municipal CCTV. Image labeling has been used by Google Image Labeler to detect products in photos and allow people to search based on a photo. Image labeling has also been demonstrated to generate speech to describe images to blind people.

Machine learning can help to restore and attribute ancient texts. It can help to index texts, e.g., to enable better and easier searching and classification of fragments.

AI can also be used to investigate genomes to uncover genetic history, such as interbreeding between archaic and modern humans by which, e.g., the past existence of a ghost population, not Neanderthal or Denisovan, was inferred. It can also be used for "non-invasive and non-destructive access to internal structures of archaeological remains".

A deep learning system was reported to learn intuitive physics from visual data (of virtual 3D environments) based on an unpublished approach inspired by studies of visual cognition in infants. Other researchers have developed a machine learning algorithm that could discover sets of basic variables of various physical systems and predict the systems' future dynamics from video recordings of their behavior. In the future, it may be possible that such can be used to automate the discovery of physical laws of complex systems.

Machine learning is used in diverse types of reverse engineering. For example, machine learning has been used to reverse engineer a composite material part, enabling unauthorized production of high quality parts, and for quickly understanding the behavior of malware. It can be used to reverse engineer AI models. It can also design components by engaging in a type of reverse engineering of not-yet existent virtual components, such as inverse molecular design for particular desired functionality or protein design for pre-specified functional sites. Biological network reverse engineering could model interactions in a human understandable way, e.g., based on time-series data of gene expression levels. The open-source Reverse Engineer Anything (REA) project connects AI coding agents with reverse-engineering tools such as Ghidra, Hopper, and IDA to inspect compiled binaries and trace application behavior.

AI is used in astronomy to analyze increasing amounts of available data and applications, mainly for "classification, regression, clustering, forecasting, generation, discovery, and the development of new scientific insights" e.g., for discovering exoplanets, forecasting solar activity, and distinguishing between signals and instrumental effects in gravitational wave astronomy. It could also be used for space exploration, including analysis of data from space missions, real-time science decisions of spacecraft, space debris avoidance, and more autonomous operation. In the search for extraterrestrial intelligence (SETI), machine learning has been used in attempts to identify artificially generated electromagnetic waves in available data—such as real-time observations—and other technosignatures, e.g. via anomaly detection. In ufology, the SkyCAM-5 project headed by Prof. Hakan Kayal and the Galileo Project headed by Avi Loeb use machine learning to attempt to detect and classify types of UFOs. The Galileo Project also seeks to detect two further types of potential extraterrestrial technological signatures with the use of AI: 'Oumuamua-like interstellar objects, and non-manmade artificial satellites. Machine learning can also be used to produce datasets of spectral signatures of molecules that may be involved in the atmospheric production or consumption of particular chemicals—such as phosphine possibly detected on Venus—which could prevent miss assignments and, if accuracy is improved, be used in future detection and identification of molecules on other planets.

There is research about which types of computer-aided chemistry would benefit from machine learning. A deep learning AI-based process has been developed that uses genome databases to design novel proteins based on evolutionary algorithms. Machine learning has also been used for protein design with pre-specified functional sites, predicting molecular properties, and exploring large chemical/reaction spaces. Using drug discovery AI algorithms, researchers generated 40,000 potential chemical weapon candidates, helping in the regulation of such chemicals to prevent synthesizing them for real harm. Applications for machine learning in decoding human biology include helping to map gene expression patterns to functional activation patterns or identifying functional DNA motifs. It is widely used in genetic research. There is some use of machine learning in synthetic biology, disease biology, nanotechnology (e.g., nanostructured materials and bionanotechnology), and materials science.