Improved sales forecasts for individual products in retail stores can have a positive effect both environmentally and economically. Historically these forecasts have been done through a combination of statistical measurements and experience. However, with the increased computational power available in modern computers, there has been an interest in applying machine learning for this problem. The aim of this thesis was to utilize two years of sales data, yearly calendar events, and weather data to investigate which machine learning method could forecast sales the best. The investigated methods were XGBoost, ARIMAX, LSTM, and Facebook Prophet. Overall the XGBoost and LSTM models performed the best and had a lower mean absolute value and symmetric mean percentage absolute error compared to the other models. However, Facebook Prophet performed the best in regards to root mean squared error and mean absolute error during the holiday season, indicating that Facebook Prophet was the best model for the holidays. The LSTM model could however quickly adapt during the holiday season improved the performance. Furthermore, the inclusion of weather did not improve the models significantly, and in some cases, the results were worsened. Thus, the results are inconclusive but indicate that the best model is dependent on the time period and goal of the forecast. / Förbättrade försäljningsprognoser för individuella produkter inom detaljhandeln kan leda till både en miljömässig och ekonomisk förbättring. Historiskt sett har dessa utförts genom en kombination av statistiska metoder och erfarenhet. Med den ökade beräkningskraften hos dagens datorer har intresset för att applicera maskininlärning på dessa problem ökat. Målet med detta examensarbete är därför att undersöka vilken maskininlärningsmetod som kunde prognostisera försäljning bäst. De undersökta metoderna var XGBoost, ARIMAX, LSTM och Facebook Prophet. Generellt presterade XGBoost och LSTM modellerna bäst då dem hade ett lägre mean absolute value och symmetric mean percentage absolute error jämfört med de andra modellerna. Dock, gällande root mean squared error hade Facebook Prophet bättre resultat under högtider, vilket indikerade att Facebook Prophet var den bäst lämpade modellen för att förutspå försäljningen under högtider. Dock, kunde LSTM modellen snabbt anpassa sig och förbättrade estimeringarna. Inkluderingen av väderdata i modellerna resulterade inte i några markanta förbättringar och gav i vissa fall även försämringar. Övergripande, var resultaten tvetydiga men indikerar att den bästa modellen är beroende av prognosens tidsperiod och mål.

Applications for sensor-based human activity recognition use the latest algorithms for the detection and classification of human everyday activities, both for online and offline use cases. The insights generated by those algorithms can in a next step be used within a wide broad of applications such as safety, fitness tracking, localization, personalized health advice and improved child and elderly care.In order for an algorithm to be performant, a significant amount of annotated data from a specific target audience is required. However, a satisfying data collection process is cost and labor intensive. This also may be unfeasible for specific target groups as aging effects motion patterns and behaviors. One main challenge in this application area lies in the ability to identify relevant changes over time while being able to reuse previously annotated user data. The accurate detection of those user-specific patterns and movement behaviors therefore requires individual and adaptive classification models for human activities.The goal of this degree work is to compare several supervised classifier performances when trained and tested on a newly iterative user-specific human activity classification approach as described in this report. A qualitative and quantitative data collection process was applied. The tree-based classification algorithms Decision Tree, Random Forest as well as XGBoost were tested on custom based datasets divided into three groups. The datasets contained labeled motion data of 21 volunteers from wrist worn sensors.Computed across all datasets, the average performance measured in recall increased by 5.2% (using a simulated leave-one-subject-out cross evaluation) for algorithms trained via the described approach compared to a random non-iterative approach. / Sensorbaserad aktivitetsigenkänning använder sig av det senaste algoritmerna för detektion och klassificering av mänskliga vardagliga aktiviteter, både i uppoch frånkopplat läge. De insikter som genereras av algoritmerna kan i ett nästa steg användas inom en mängd nya applikationer inom områden så som säkerhet, träningmonitorering, platsangivelser, personifierade hälsoråd samt inom barnoch äldreomsorgen.För att en algoritm skall uppnå hög prestanda krävs en inte obetydlig mängd annoterad data, som med fördel härrör från den avsedda målgruppen. Dock är datainsamlingsprocessen kostnadsoch arbetsintensiv. Den kan dessutom även vara orimlig att genomföra för vissa specifika målgrupper, då åldrandet påverkar rörelsemönster och beteenden. En av de största utmaningarna inom detta område är att hitta de relevanta förändringar som sker över tid, samtidigt som man vill återanvända tidigare annoterad data. För att kunna skapa en korrekt bild av det individuella rörelsemönstret behövs därför individuella och adaptiva klassificeringsmodeller.Målet med detta examensarbete är att jämföra flera olika övervakade klassificerares (eng. supervised classifiers) prestanda när dem tränats med hjälp av ett iterativt användarspecifikt aktivitetsklassificeringsmetod, som beskrivs i denna rapport. En kvalitativ och kvantitativ datainsamlingsprocess tillämpades. Trädbaserade klassificeringsalgoritmerna Decision Tree, Random Forest samt XGBoost testades utifrån specifikt skapade dataset baserade på 21 volontärer, som delades in i tre grupper. Data är baserad på rörelsedata från armbandssensorer.Beräknat över samtlig data, ökade den genomsnittliga sensitiviteten med 5.2% (simulerad korsvalidering genom utelämna-en-individ) för algoritmer tränade via beskrivna metoden jämfört med slumpvis icke-iterativ träning.

Within demand forecasting, and specifically within the field of e-commerce, the provided data often contains erratic behaviours which are difficult to explain. This induces contradictions to the common assumptions within classical approaches for time series analysis. Yet, classical and naive approaches are still commonly used. Machine learning could be used to alleviate such problems. This thesis evaluates four models together with Swedish fin-tech company QLIRO AB. More specifically, a MLR (Multiple Linear Regression) model, a classic Box-Jenkins model (SARIMAX), an XGBoost model, and a LSTM-network (Long Short-Term Memory). The provided data consists of aggregated total daily reservations by e-merchants within the Nordic market from 2014. Some data pre processing was required and a smoothed version of the data set was created for comparison. Each model was constructed according to their specific requirements but with similar feature engineering. Evaluation was then made on a monthly level with a forecast horizon of 30 days during 2021. The results shows that both the MLR and the XGBoost provides the most consistent results together with perks for being easy to use. After these two, the LSTM-network showed the best results for November and December on the original data set but worst overall. Yet it had good performance on the smoothed data set and was then comparable to the first two. The SARIMAX was the worst performing of all the models considered in this thesis and was not as easy to implement. / Inom efterfrågeprognoser, och specifikt inom området e-handel, innehåller den tillhandahållna informationen ofta oberäkneliga beteenden som är svåra att förklara. Detta motsäger vanliga antaganden inom tidsserier som används för de mer klassiska tillvägagångssätten. Ändå är klassiska och naiva metoder fortfarande vanliga. Maskininlärning skulle kunna användas för att lindra sådana problem. Detta examensarbete utvärderar fyra modeller tillsammans med det svenska fintechföretaget QLIRO AB. Mer specifikt en MLR-modell (Multiple Linear Regression), en klassisk Box-Jenkins-modell (SARIMAX), en XGBoost-modell och ett LSTM-nätverk (Long Short-Term Memory). Den tillhandahållna informationen består av aggregerade dagliga reservationer från e-handlare inom den nordiska marknaden från 2014. Viss dataförbehandling krävdes och en utjämnad version av datamängden skapades för jämförelse. Varje modell konstruerades enligt deras specifika krav men med liknande \textit{feature engineering}. Utvärderingen gjordes sedan på månadsnivå med en prognoshorisont på 30 dagar under 2021. Resultaten visar att både MLR och XGBoost ger de mest pålitliga resultaten tillsammans med fördelar som att vara lätta att använda. Efter dessa visar LSTM-nätverket de bästa resultaten för november och december på den ursprungliga datamängden men sämst totalt sett. Ändå visar den god prestanda på den utjämnade datamängden och var sedan jämförbar med de två första modellerna. SARIMAX var den sämst presterande av alla jämförda modeller och inte lika lätt att implementera.

This thesis intends to evaluate the feasibility of supervised learning models for predicting house prices on the countryside of South Sweden. It is essential for mortgage lenders to have accurate housing valuation algorithms and the current model offered by Booli is not accurate enough when evaluating residence prices on the countryside. Different types of boosted decision trees were implemented to address this issue and their performances were compared to traditional machine learning methods. These different types of supervised learning models were implemented in order to find the best model with regards to relevant evaluation metrics such as root-mean-squared error (RMSE) and mean absolute percentage error (MAPE). The implemented models were ridge regression, lasso regression, random forest, AdaBoost, gradient boosting, CatBoost, XGBoost, and LightGBM. All these models were benchmarked against Booli's current housing valuation algorithms which are based on a k-NN model. The results from this thesis indicated that the LightGBM model is the optimal one as it had the best overall performance with respect to the chosen evaluation metrics. When comparing the LightGBM model to the benchmark, the performance was overall better, the LightGBM model had an RMSE score of 0.330 compared to 0.358 for the Booli model, indicating that there is a potential of using boosted decision trees to improve the predictive accuracy of residence prices on the countryside. / Denna uppsats ämnar utvärdera genomförbarheten hos olika övervakade inlärningsmodeller för att förutse huspriser på landsbygden i Södra Sverige. Det är viktigt för bostadslånsgivare att ha noggranna algoritmer när de värderar bostäder, den nuvarande modellen som Booli erbjuder har dålig precision när det gäller värderingar av bostäder på landsbygden. Olika typer av boostade beslutsträd implementerades för att ta itu med denna fråga och deras prestanda jämfördes med traditionella maskininlärningsmetoder. Dessa olika typer av övervakad inlärningsmodeller implementerades för att hitta den bästa modellen med avseende på relevanta prestationsmått som t.ex. root-mean-squared error (RMSE) och mean absolute percentage error (MAPE). De övervakade inlärningsmodellerna var ridge regression, lasso regression, random forest, AdaBoost, gradient boosting, CatBoost, XGBoost, and LightGBM. Samtliga algoritmers prestanda jämförs med Boolis nuvarande bostadsvärderingsalgoritm, som är baserade på en k-NN modell. Resultatet från denna uppsats visar att LightGBM modellen är den optimala modellen för att värdera husen på landsbygden eftersom den hade den bästa totala prestandan med avseende på de utvalda utvärderingsmetoderna. LightGBM modellen jämfördes med Booli modellen där prestandan av LightGBM modellen var i överlag bättre, där LightGBM modellen hade ett RMSE värde på 0.330 jämfört med Booli modellen som hade ett RMSE värde på 0.358. Vilket indikerar att det finns en potential att använda boostade beslutsträd för att förbättra noggrannheten i förutsägelserna av huspriser på landsbygden.

Orientador: Anna Diva Plasencia Lotufo / Abstract: Many environmental, economic and societal factors are leading fire brigades to be increasingly solicited, and, as a result, they face an ever-increasing number of interventions, most of the time on constant resource. On the other hand, these interventions are directly related to human activity, which itself is predictable: swimming pool drownings occur in summer while road accidents due to ice storms occur in winter. One solution to improve the response of firefighters on constant resource is therefore to predict their workload, i.e., their number of interventions per hour, based on explanatory variables conditioning human activity. The present work aims to develop three models that are compared to determine if they can predict the firefighters' response load in a reasonable way. The tools chosen are the most representative from their respective categories in Machine Learning, such as XGBoost having as core a decision tree, a classic method such as Multi-Layer Perceptron and a more advanced algorithm like Long Short-Term Memory both with neurons as a base. The entire process is detailed, from data collection to obtaining the predictions. The results obtained prove a reasonable quality prediction that can be improved by data science techniques such as feature selection and adjustment of hyperparameters. / Resumo: Muitos fatores ambientais, econômicos e sociais estão levando as brigadas de incêndio a serem cada vez mais solicitadas e, como consequência, enfrentam um número cada vez maior de intervenções, na maioria das vezes com recursos constantes. Por outro lado, essas intervenções estão diretamente relacionadas à atividade humana, o que é previsível: os afogamentos em piscina ocorrem no verão, enquanto os acidentes de tráfego, devido a tempestades de gelo, ocorrem no inverno. Uma solução para melhorar a resposta dos bombeiros com recursos constantes é prever sua carga de trabalho, isto é, seu número de intervenções por hora, com base em variáveis explicativas que condicionam a atividade humana. O presente trabalho visa desenvolver três modelos que são comparados para determinar se eles podem prever a carga de respostas dos bombeiros de uma maneira razoável. As ferramentas escolhidas são as mais representativas de suas respectivas categorias em Machine Learning, como o XGBoost que tem como núcleo uma árvore de decisão, um método clássico como o Multi-Layer Perceptron e um algoritmo mais avançado como Long Short-Term Memory ambos com neurônios como base. Todo o processo é detalhado, desde a coleta de dados até a obtenção de previsões. Os resultados obtidos demonstram uma previsão de qualidade razoável que pode ser melhorada por técnicas de ciência de dados, como seleção de características e ajuste de hiperparâmetros. / Mestre

The new Health 4.0 concept brings the idea of combining modern technologies from field of science and technology with research in healthcare and medicine. This work realizes a system of secured actigraph data transfer and preprocessing based on the concept of Health 4.0. The system is successfully designed, implemented, tested and secured. With the help of a non-invasive method of monitoring the movement and temperature of the subject using the GENEActiv actigraph allows the system to securely transfer, process and evaluate the subject's sleep data using the machine learning algorithm XGBoost. The proposed system is in accordance with the valid law of the Czech Republic and meets legal requirements.

Background: A problematic area in today’s large scale distributed systems is the exponential amount of growing log data. Finding anomalies by observing and monitoring this data with manual human inspection methods becomes progressively more challenging, complex and time consuming. This is vital for making these systems available around-the-clock. Aim: The main objective of this study is to determine which are the most suitable Machine Learning (ML) algorithms and if they can live up to needs and requirements regarding optimization and efficiency in the log data monitoring area. Including what specific steps of the overall problem can be improved by using these algorithms for anomaly detection and classification on different real provided data logs. Approach: Initial pre-study is conducted, logs are collected and then preprocessed with log parsing tool Drain and regular expressions. The approach consisted of a combination of K-Means + XGBoost and respectively Principal Component Analysis (PCA) + K-Means + XGBoost. These was trained, tested and with different metrics individually evaluated against two datasets, one being a Server data log and on a HTTP Access log. Results: The results showed that both approaches performed very well on both datasets. Able to with high accuracy, precision and low calculation time classify, detect and make predictions on log data events. It was further shown that when applied without dimensionality reduction, PCA, results of the prediction model is slightly better, by a few percent. As for the prediction time, there was marginally small to no difference for when comparing the prediction time with and without PCA. Conclusions: Overall there are very small differences when comparing the results for with and without PCA. But in essence, it is better to do not use PCA and instead apply the original data on the ML models. The models performance is generally very dependent on the data being applied, it the initial preprocessing steps, size and it is structure, especially affecting the calculation time the most.

In the context of providing credit online to customers in retail shops, the provider must perform risk assessments quickly and often based on scarce historical data. This can be achieved by automating the process with Machine Learning algorithms. Gradient Boosting Tree algorithms have demonstrated to be capable in a wide range of application scenarios. However, they are yet to be implemented for predicting the profitability of new customers based solely on the customers’ first purchases. This study aims to evaluate the predictive performance of the XGBoost, LightGBM, and CatBoost algorithms in this context. The Recall and Precision metrics were used as the basis for assessing the models’ performance. The experiment implemented for this study shows that the model displays similar capabilities while also being biased towards the majority class.

During the broadcast of a golf tournament, a way to show the audience what a player's swing looks like would be to draw a trace following the movement of the club head. A computer vision model can be trained to identify the position of the club head in an image, but due to the high speed at which professional players swing their clubs coupled with the low frame rate of a typical broadcast camera, the club head is not discernible whatsoever in most frames. This means that the computer vision model is only able to deliver a few sparse detections of the club head. This thesis project aims to develop a machine learning model that can predict the complete motion of the club head, in the form of a swing trace, based on the sparse club head detections. Slow motion videos of golf swings are collected, and the club head's position is annotated manually in each frame. From these annotations, relevant data to describe the club head's motion, such as position and time parameters, is extracted and used to train the machine learning models. The dataset contains 256 annotated swings of professional and competent amateur golfers. The two models that are implemented in this project are XGBoost and a feed forward neural network. The input given to the models only contains information in specific parts of the swing to mimic the pattern of the sparse detections. Both models learned the underlying physics of the golf swing, and the quality of the predicted traces depends heavily on the amount of information provided in the input. In order to produce good predictions with only the amount of input information that can be expected from the computer vision model, a lot more training data is required. The traces predicted by the neural network are significantly smoother and thus look more realistic than the predictions made by the XGBoost model.

No description available.