L’objectif de cette recherche était d’évaluer l’efficacité du paramètre de classification pour prédire suivre les tendances boursières. Les méthodes traditionnelles basées sur la prévision, qui ciblent l’immédiat pas de temps suivant, rencontrent souvent des défis dus à des données non stationnaires, compromettant le modèle précision et stabilité. En revanche, notre approche de classification prédit une évolution plus large du cours des actions avec des mouvements sur plusieurs pas de temps, visant à réduire la non-stationnarité des données. Notre ensemble de données, dérivé de diverses actions du NASDAQ-100 et éclairé par plusieurs indicateurs techniques, a utilisé un mélange d'experts composé d'un mécanisme de déclenchement souple et d'une architecture basée sur les transformateurs. Bien que la méthode principale de cette expérience ne se soit pas révélée être aussi réussie que nous l'avions espéré et vu initialement, la méthodologie avait la capacité de dépasser toutes les lignes de base en termes de performance dans certains cas à quelques époques, en démontrant le niveau le plus bas taux de fausses découvertes tout en ayant un taux de rappel acceptable qui n'est pas zéro. Compte tenu de ces résultats, notre approche encourage non seulement la poursuite des recherches dans cette direction, dans lesquelles un ajustement plus précis du modèle peut être mis en œuvre, mais offre également aux personnes qui investissent avec l'aide de l'apprenstissage automatique un outil différent pour prédire les tendances boursières, en utilisant un cadre de classification et un problème défini différemment de la norme. Il est toutefois important de noter que notre étude est basée sur les données du NASDAQ-100, ce qui limite notre l’applicabilité immédiate du modèle à d’autres marchés boursiers ou à des conditions économiques variables. Les recherches futures pourraient améliorer la performance en intégrant les fondamentaux des entreprises et effectuer une analyse du sentiment sur l'actualité liée aux actions, car notre travail actuel considère uniquement indicateurs techniques et caractéristiques numériques spécifiques aux actions. / The objective of this research was to evaluate the classification setting's efficacy in predicting stock market trends. Traditional forecasting-based methods, which target the immediate next time step, often encounter challenges due to non-stationary data, compromising model accuracy and stability. In contrast, our classification approach predicts broader stock price movements over multiple time steps, aiming to reduce data non-stationarity. Our dataset, derived from various NASDAQ-100 stocks and informed by multiple technical indicators, utilized a Mixture of Experts composed of a soft gating mechanism and a transformer-based architecture. Although the main method of this experiment did not prove to be as successful as we had hoped and seen initially, the methodology had the capability in surpassing all baselines in certain instances at a few epochs, demonstrating the lowest false discovery rate while still having an acceptable recall rate. Given these results, our approach not only encourages further research in this direction, in which further fine-tuning of the model can be implemented, but also offers traders a different tool for predicting stock market trends, using a classification setting and a differently defined problem. It's important to note, however, that our study is based on NASDAQ-100 data, limiting our model's immediate applicability to other stock markets or varying economic conditions. Future research could enhance performance by integrating company fundamentals and conducting sentiment analysis on stock-related news, as our current work solely considers technical indicators and stock-specific numerical features.

Knowledge tracing is concerned with tracking a student’s knowledge as she/he engages with exercises in an (online) learning platform. A commonly used state-of-theart knowledge tracing model is Deep Knowledge Tracing (DKT) which models the time dimension as a sequence of completed exercises per student by using a Long Short-Term Memory Neural Network (LSTM). However, a common problem in this sequence-based model is too much instability in the time dimension of the modelled knowledge of a student. In other words, the student’s knowledge on a skill changes too quickly and unreliably. We propose dynamic student embeddings as a stable method for encoding the time dimension of knowledge tracing systems. In this method the time dimension is encoded in time slices of a fixed size, while the model’s loss function is designed to smoothly align subsequent time slices. We compare the dynamic student embeddings to DKT on a large-scale real-world dataset, and we show that dynamic student embeddings provide a more stable knowledge tracing while retaining good performance. / Kunskapsspårning handlar om att modellera en students kunskaper då den arbetar med uppgifter i en (online) lärplattform. En vanlig state-of-the-art kunskapsspårningsmodell är Deep Knowledge Tracing (DKT) vilken modellerar tidsdimensionen som en sekvens av avslutade uppgifter per student med hjälp av ett neuronnät kallat Long Short-Term Memory Neural Network (LSTM). Ett vanligt problem i dessa sekvensbaserade modeller är emellertid en för stor instabilitet i tidsdimensionen för studentens modellerade kunskap. Med andra ord, studentens kunskaper förändras för snabbt och otillförlitligt. Vi föreslår därför Dynamiska Studentvektorer som en stabil metod för kodning av tidsdimensionen för kunskapsspårningssystem. I denna metod kodas tidsdimensionen i tidsskivor av fix storlek, medan modellens förlustfunktion är utformad för att smidigt justera efterföljande tidsskivor. I denna uppsats jämför vi de Dynamiska Studentvektorer med DKT i en storskalig verklighetsbaserad dataset, och visar att Dynamiska Studentvektorer tillhandahåller en stabilare kunskapsspårning samtidigt som prestandan bibehålls.

Real-time prediction of taxi demand in a discrete geographical space is useful as it can minimise service disequilibrium by informing idle drivers of the imbalance, incentivising them to reduce it. This, in turn, can lead to improved efficiency, more stimulating work conditions, and a better customer experience. This study aims to investigate the possibility of utilising an artificial neural network model to make such a prediction for Stockholm. The model was trained on historical demand data and - uniquely - crowd flow data from a cellular provider (aggregated and anonymised). Results showed that the final model could generate very helpful predictions (only off by less than 1 booking on average). External factors - including crowd flow data - had a minor positive impact on performance, but limitations regarding the setup of the zones lead to the study being unable to make a definitive conclusion about whether crowd flow data is effective in improving taxi demand predictors or not. / Prognos av taxiefterfrågan i ett diskret geografiskt utrymme är användbart då det kan minimera obalans mellan utbud och efterfrågan genom att informera lediga taxiförare om obalansen och därmed utjämna den. Detta kan i sin tur leda till förbättrad effektivitet, mer stimulerande arbetsförhållanden och en bättre kundupplevelse. Denna studie ämnar att undersöka möjligheten att använda artificiella neurala nätverk för att göra en sådan prognos för Stockholm. Modellen tränades på historisk data om efterfrågan och - unikt för studien - folkströmsdata (aggregerad och anonymiserad) från en mobiloperatör. Resultaten visade att den slutgiltiga modellen kunde generera användbara prognoser (med ett genomsnittligt prognosfel med mindre än 1 bil per tidsenhet). Externa faktorer – inklusive folkströmsdata – hade en märkbar positiv inverkan på prestandan, men begränsningar rörande framställningen av zonerna ledde till att studien inte kunde dra en definitiv slutsats om huruvida folkströmsdata är effektiva för att förbättra prognoser för taxiefterfrågan eller ej.

<div>The compressed air system is widely used throughout the industry. Air compressors are one of the most costly systems to operate in industrial plants in therms of energy consumption. Therefore, it becomes one of the primary target when it comes to electrical energy and load management practices. Load forecasting is the first step in developing energy management systems both on the supply and user side. A comprehensive literature review has been conducted, and there was a need to study if predicting compressed air system’s load is a possibility. </div><div><br></div><div>System’s load profile will be valuable to the industry practitioners as well as related software providers in developing better practice and tools for load management and look-ahead scheduling programs. Feed forward neural networks (FFNN) and long short-term memory (LSTM) techniques have been used to perform 15 minutes ahead prediction. Three cases of different sizes and control methods have been studied. The results proved the possibility of the forecast. In this study two control methods have been developed by using the prediction. The first control method is designed for variable speed driven air compressors. The goal was to decrease the maximum electrical load for the air compressor by using the system's full operational capabilities and the air receiver tank. This goal has been achieved by optimizing the system operation and developing a practical control method. The results can be used to decrease the maximum electrical load consumed by the system as well as assuring the sufficient air for the users during the peak compressed air demand by users. This method can also prevent backup or secondary systems from running during the peak compressed air demand which can result in more energy and demand savings. Load management plays a pivotal role and developing maximum load reduction methods by users can result in more sustainability as well as the cost reduction for developing sustainable energy production sources. The last part of this research is concentrated on reducing the energy consumed by load/unload controlled air compressors. Two novel control methods have been introduced. One method uses the prediction as input, and the other one doesn't require prediction. Both of them resulted in energy consumption reduction by increasing the off period with the same compressed air output or in other words without sacrificing the required compressed air needed for production.</div><div><br></div>

This thesis proposes a deep learning anomaly detection pipeline to detect possible anomalies during the operation of a fleet of batteries and presents its development and evaluation. The pipeline employs sensors that connect to each battery in the fleet to remotely collect real-time measurements of their operating characteristics, such as voltage, current, and temperature. The deep learning based time-series anomaly detection model was developed using Variational Autoencoder (VAE) architecture that utilizes either Long Short-Term Memory (LSTM) or, its cousin, Gated Recurrent Unit (GRU) as the encoder and the decoder networks (LSTMVAE and GRUVAE). Both variants were evaluated against three well-known conventional anomaly detection algorithms Isolation Nearest Neighbour (iNNE), Isolation Forest (iForest), and kth Nearest Neighbour (k-NN) algorithms. All five models were trained using two variations in the training dataset (full-year dataset and partial recent dataset), producing a total of 10 different model variants. The models were trained using the unsupervised method and the results were evaluated using a test dataset consisting of a few known anomaly days in the past operation of the customer’s battery fleet. The results demonstrated that k-NN and GRUVAE performed close to each other, outperforming the rest of the models with a notable margin. LSTMVAE and iForest performed moderately, while the iNNE and iForest variant trained with the full dataset, performed the worst in the evaluation. A general observation also reveals that limiting the training dataset to only a recent period produces better results nearly consistently across all models. / Detta examensarbete föreslår en pipeline för djupinlärning av avvikelser för att upptäcka möjliga anomalier under driften av en flotta av batterier och presenterar dess utveckling och utvärdering. Rörledningen använder sensorer som ansluter till varje batteri i flottan för att på distans samla in realtidsmätningar av deras driftsegenskaper, såsom spänning, ström och temperatur. Den djupinlärningsbaserade tidsserieanomalidetekteringsmodellen utvecklades med VAE-arkitektur som använder antingen LSTM eller, dess kusin, GRU som kodare och avkodarnätverk (LSTMVAE och GRU) VAE). Båda varianterna utvärderades mot tre välkända konventionella anomalidetekteringsalgoritmer -iNNE, iForest och k-NN algoritmer. Alla fem modellerna tränades med hjälp av två varianter av träningsdatauppsättningen (helårsdatauppsättning och delvis färsk datauppsättning), vilket producerade totalt 10 olika modellvarianter. Modellerna tränades med den oövervakade metoden och resultaten utvärderades med hjälp av en testdatauppsättning bestående av några kända anomalidagar under tidigare drift av kundens batteriflotta. Resultaten visade att k-NN och GRUVAE presterade nära varandra och överträffade resten av modellerna med en anmärkningsvärd marginal. LSTMVAE och iForest presterade måttligt, medan varianten iNNE och iForest tränade med hela datasetet presterade sämst i utvärderingen. En allmän observation avslöjar också att en begränsning av träningsdatauppsättningen till endast en ny period ger bättre resultat nästan konsekvent över alla modeller.