Paper covers image classification using the Keras API in TensorFlow. The dataset used is a set of labelled images consisting of characters from the Pokémon media franchise. In order to artificially generate additional data, the process of data augmentation has been applied on the initial dataset to reduce overfitting. A comparison between DenseNet-121, DenseNet-169 and DenseNet-201 has been made to observe which of the models scores a greater accuracy. A Graphics Processing Unit (GPU) has been set up to work with TensorFlow in order to efficiently train the model.

This paper presents the use of different prediction algorithms in order to recognise the popularity of a song. That recognition gives features that are directly affecting popularity of a song. For this research, data from several hundreds of the most popular songs were used in combination with songs that often appear on different playlists from different musicians. The reason for this mixing of songs is done to ensure that the model works as efficiently as possible by comparing popular songs features with those of that are no longer trending. The processing of the collected data gave an excellent insight into the importance of certain factors on the popularity of a certain song. As a result of research, month of release, acoustics and tempo were represented as features that are mostly correlated with popularity. Through the processing and analysis of a large amount of data, four models were created using different algorithms. Algorithms that were used are Decision Tree, Nearest Neighbour Classifier, Random Forest and Support Vector Classifier algorithms. The best results were achieved by training the model with the Decision Tree algorithm and accuracy of 100%.

Predictive modelling and AI have become a ubiquitous part of many modern industries and provide promising opportunities for more accurate analysis, better decision-making, reducing risk and improving profitability. One of the most promising applications for these technologies is in the financial sector as these could be influential for fraud detection, credit risk, creditworthiness and payment analysis. By using machine learning algorithms for analysing larger datasets, financial institutions could identify patterns and anomalies that could indicate fraudulent activity, allowing them to take action in real-time and minimize losses. This paper aims to explore the application of predictive models for assessing customer worthiness, identify the benefits and risks involved with this approach and compare their results in order to provide insights into which model performs best in the given context.

The vehicle routing problem is one of the most complex problems in the field of combinatorial optimization. Creating optimal routes leads to timely delivery of orders to end customers, which increases the efficiency of the company and enables maximum earnings. The problem of vehicle routing with a series of real-world constraints is called the rich vehicle routing problem (RVRP). The paper presents an approach to solving RVRP, where the asymmetric routing problem with a heterogeneous vehicle fleet, time windows, customer-vehicle constraints and a number of others is observed. The approach solves the problem in two phases, by dividing customers into clusters using a discrete metaheuristic Bat algorithm, and by solving the routing problem for each obtained cluster. The proposed approach has been tested for 26 days of delivery from large warehouses in Bosnia and Herzegovina. Significant savings were achieved compared to previously implemented approaches. All created routes were feasible. The approach automatically creates routes, and gives results in a shorter time than previously used approaches. Time does not increase significantly with the increase in the number of customers, which is a great advantage of the proposed approach.

By successfully solving the problem of forecasting, the processes in the work of various companies are optimized and savings are achieved. In this process, the analysis of time series data is of particular importance. Since the creation of Facebook’s Prophet, and Amazon’s DeepAR+ and CNN-QR forecasting models, algorithms have attracted a great deal of attention. The paper presents the application and comparison of the above algorithms for sales forecasting in distribution companies. A detailed comparison of the performance of algorithms over real data with different lengths of sales history was made. The results show that Prophet gives better results for items with a longer history and frequent sales, while Amazon’s algorithms show superiority for items without a long history and items that are rarely sold.

Distribution companies often store goods in large warehouses. Orders are collected and prepared for transport. Large-scale warehouses are often divided into sectors. Each worker collects a part of the order from the assigned sector. In that case, workers often pick small orders and the process is not optimal. Therefore, order batching is done, where one worker collects multiple orders at a time. In this paper, an innovative concept of orders batching in a warehouse with a 48-hour delivery based on a metaheuristic approach is described. The algorithm divides each order by sectors. An analysis of each part of the order is done and the possibility of batching based on the order content is checked. The order batching is based on the discrete Bat algorithm. The transport scheme and the order of loading goods into the truck are observed. In the order picking process, a number of standard constraints such as weight and item priorities are considered. The concept has been implemented and tested for 50 days of warehouse operation in one of the largest warehouses in Bosnia and Herzegovina. The algorithm is compared with the earlier approach of collecting orders in the warehouse, and significant progress has been observed in the number of kilometers traveled on a daily basis.

—The problem of transport optimization is of great importance for the successful operation of distribution companies. To successfully find routes, it is necessary to provide accurate input data on orders, customer location, vehicle fleet, depots, and delivery restrictions. Most of the input data can be provided through the order creation process or the use of various online services. One of the most important inputs is an estimate of the unloading time of the goods for each customer. The number of customers that the vehicle serves during the day directly depends on the time of unloading. This estimate depends on the number of items, weight and volume of orders, but also on the specifics of customers, such as the proximity of parking or crowds at the unloading location. Customers repeat over time, and unloading time can be calculated from GPS data history. The paper describes the innovative application of machine learning techniques and delivery history obtained through a GPS vehicle tracking system for a more accurate estimate of unloading time. The application of techniques gave quality results and significantly improved the accuracy of unloading time data by 83.27% compared to previously used methods. The proposed method has been implemented for some of the largest distribution companies in Bosnia and Herzegovina.

ABSTRACT Transportation management, as a part of the supply chain management, is a complex process that consists of planning and delivering goods to customers. The paper presents a complete multi-phase intelligent and adaptive transportation management system, which includes data collection, parameter tuning, and the heuristic algorithm based on the Tabu search for vehicle routing. The paper describes the procedure for collecting Global Positioning System (GPS) data and analyzing the compliance with the proposed routes based on the data collected. The described routing algorithm is powerful and supports many real-world limitations. An algorithm for the anomaly detection in the GPS data is presented as well as the usage of collected GPS data to improve the future results of the algorithm. The concept was implemented and tested on real data in some of the largest distribution companies in Bosnia and Herzegovina. The proposed approach resulted with more than satisfactory results in real-world application.