Compared to other industries, fashion apparel retail faces many challenges in predicting future demand for its products with a high degree of precision. Fashion products’ short life cycle, insufficient historical information, highly uncertain market demand, and periodic seasonal trends necessitate the use of models that can contribute to the efficient forecasting of products’ sales and demand. Many researchers have tried to address this problem using conventional forecasting models that predict future demands using historical sales information. While these models predict product demand with fair to moderate accuracy based on previously sold stock, they cannot fully be used for predicting future demands due to the transient behaviour of the fashion industry. This paper proposes an intelligent forecasting system that combines image feature attributes of clothes along with its sales data to predict future demands. The data used for this empirical study is from a European fashion retailer, and it mainly contains sales information on apparel items and their images. The proposed forecast model is built using machine learning and deep learning techniques, which extract essential features of the product images. The model predicts weekly sales of new fashion apparel by finding its best match in the clusters of products that we created using machine learning clustering based on products’ sales profiles and image similarity. The results demonstrated that the performance of our proposed forecast model on the tested or test items is promising, and this model could be effectively used to solve forecasting problems.

Data analytics is pervasive in retailing as a key tool to gain customer insights. Often, the data sets used are large, but also rich, i.e., they contain specific information, including demographic details, about individual customers. Typical usage of the analytics include personalized recommendations, churn prediction and estimating customer life-time value. In this application paper, an investigation is carried out using a very large real-world data set from the fashion retailing industry, containing only limited information. Specifically, while the purchases can be connected to individual customers, there is no additional information available about the customers. With this in mind, the main purpose is to discover what the company can learn about their business and their customers as a group, based on the available data. The exploratory analysis uses data from four years, where each year has more than 1 million customers and 6 million transactions. Using traditional RFM (Recency, Frequency and Monetary) analysis, including looking at the transitions between different segments between two years, some interesting patterns can be observed. As an example, more than half of the customers are replaced each year. In a second experiment, the possibility to predict which of the customers that are the most likely to not make a purchase the next year is examined. Interestingly enough, while the two algorithms evaluated obtained very similar f-measures; the random forest had a substantially higher precision, while the gradient boosting showed clearly better recall. In the last experiment, targeting only the customers that have remained loyal for at least three years, rule sets describing patterns and trends that are strong indicators for churn or not are inspected and analyzed.

Digitalisation allows companies to develop many new ways of interacting with customers and other stakeholders. These digital interactions typically generate data that can be stored and later processed for different objectives. Currently, the fashion and apparel industry is undergoing a disruptive transformation due to digitalisation, including a rapid increase in the generation of data in various parts of the supply chain. While most data may not be stored with data mining or other analyses in mind, collected data frequently contain very valuable information that can be exploited. Analytics, in particular the use of data-driven AI techniques, is therefore becoming a pervasive tool that is used for a large variety of purposes and in many different processes. While the popularity of Artificial Intelligence (AI) as an advanced tool for improved decision support is increasing, applications of AI within the fashion and apparel industry have historically been rather limited.

With this in mind, the overall purpose of this thesis is to, after presenting an overview of research on applications of data-driven AI in the fashion and apparel industry, demonstrate how various data sets and AI techniques can be utilised for improved decision support in different scenarios.

Whilst the thesis first investigates the impact of AI on different parts of the supply chain, the empirical work focuses on fashion and apparel retailing. Here, different AI techniques are explored in a set of case studies covering several applications in fashion and apparel retailing, thus showing the potential of data-driven AI for decision support in that domain.

One important learning outcome, found in several of the studies, is the need to combine several data sources and techniques in the projects. Another takeaway is the benefit of interpretable models, which allow for inspection and analysis of the discovered relationships. From an applied perspective, approaches like RFM modelling can be utilised as a pre-step to predict customer churn, add sentiment analysis to short-term sales forecasting and build campaign and simulation engines from historical data, which could potentially be used by many retailers.

In conclusion, this thesis has, mainly through a set of case studies addressing real-world problems and utilising real-world data sets, demonstrated how data-driven AI techniques can support and improve fashion and apparel retailers’ decision-making.

The enormous impact of artificial intelligence has been realized in transforming the fashion and apparel industry in the past decades. However, the research in this domain is scattered and mainly focuses on one of the stages of the supply chain. Due to this, it is difficult to comprehend the work conducted in the distinct domain of the fashion and apparel industry. Therefore, this paper aims to study the impact and the significance of artificial intelligence in the fashion and apparel industry in the last decades throughout the supply chain. Following this objective, we performed a systematic literature review of research articles (journal and conference) associated with artificial intelligence in the fashion and apparel industry. Articles were retrieved from two popular databases ‘‘Scopus’’ and ‘‘Web of Science’’ and the article screening was completed in five phases resulting in 149 articles. This was followed by article categorization which was grounded on the proposed taxonomy and was completed in two steps. First, the research articles were categorized according to the artificial intelligence methods applied such as machine learning, expert systems, decision support system, optimization, and image recognition and computer vision. Second, the articles were categorized based on supply chain stages targeted such as design, fabric production, apparel production, and distribution. In addition, the supply chain stages were further classified based on business-to-business (B2B) and business-to-consumer (B2C) to give a broader outlook of the industry. As a result of the categorizations, research gaps were identified in the applications of AI techniques, at the supply chain stages and from a business (B2B/B2C) perspective. Based on these gaps, the future prospects of the AI in this domain are discussed. These can benefit the researchers in academics and industrial practitioners working in the domain of the fashion and apparel industry.

This paper aims to give an overview of customer analytics in fashion retail industry in the era of big data. Fashion retail industry has been facing significant challenges since last few years due to rapidly varying customer demands. Nowadays, customers are much more informed and connected because of social media and other channels on the Internet. They demand more personalized services, and perception is not sufficient to understand our customers. Therefore, we need data to understand our customers and meet their expectation. We will discuss how customer analytics can create value in fashion retail industry, strategies and methodology to examine the consumer data. Employing and investing in these methods and technologies, industry will benefit from improved revenues, improve in sales, higher customer retention rates and thereby it will sustain in the uncertain markets. Segments are created using recency value of the customers, and their future behavior is predicted using transition matrix.

Growing use of social media such as Twitter, Instagram, Facebook, etc., by consumers leads to the vast repository of consumer generated data. Collecting and exploiting these data has been a great challenge for clothing industry. This paper aims to study the impact of Twitter on garment sales. In this direction, we have collected tweets and sales data for one of the popular apparel brands for 6 months from April 2018 – September 2018. Lexicon Approach was used to classify Tweets by sentence using Naïve Bayes model applying enhanced version of Lexicon dictionary. Sentiments were extracted from consumer tweets, which was used to map the uncertainty in forecasting model. The results from this study indicate that there is a correlation between the apparel sales and consumer tweets for an apparel brand. “Social Media Based Forecasting (SMBF)” is designed which is a fuzzy time series forecasting model to forecast sales using historical sales data and social media data. SMBF was evaluated and its performance was compared with Exponential Forecasting (EF) model. SMBF model outperforms the EF model. The result from this study demonstrated that social media data helps to improve the forecasting of garment sales and this model could be easily integrated to any time series forecasting model.

Compared to other retail industries, fashion retail industry faces many challenges to foresee future demand of its products. This is due to ever-changing choices of their consumers, who get influenced by rapidly changing market trends and it leads to the short life cycle of a fashion product. Due to the advent of e-commerce business models, fashion retailers have to put a multitude of virtual product images along with their feature information on their websites in order for their customers to know the fashion products and improve their purchasing experience. It is imperative for fashion retailers to predict future consumer preferences in advance; however, they lack advanced tools to achieve this goal. To overcome this problem, this research work combines the historical information of products with their image features using deep learning and predicts future sales. Apparel images are converted into feature vectors and then are merged with historical sales data. We applied backward propagation neural network model to predict the sales of a new product. It is found that the model performs quite well despite the small size of the dataset. This approach could be promising for forecasting the new arrivals of apparels in the market, and fashion retailers could improve their efficiency and growth.

Managing campaigns and promotions effectively is vital for the fashion retail industry. While retailers invest a lot of money in campaigns, customer retention is often very low. At innovative retailers, data-driven methods, aimed at understanding and ultimately optimizing campaigns are introduced. In this application paper, machine learning techniques are employed to analyze data about campaigns and promotions from a leading Swedish e-retailer. More specifically, predictive modeling is used to forecast the profitability and activation of campaigns using different kinds of promotions. In the empirical investigation, regression models are generated to estimate the profitability, and classification models are used to predict the overall success of the campaigns. In both cases, random forests are compared to individual tree models. As expected, the more complex ensembles are more accurate, but the usage of interpretable tree models makes it possible to analyze the underlying relationships, simply by inspecting the trees. In conclusion, the accuracy of the predictive models must be deemed high enough to make these data-driven methods attractive.

Fashion products are characterized by high variability in terms of rapidly changing consumer preferences. Consumers express their emotions on social networks such as Twitter, Facebook and Instagram. The main objective of this paper is to explore Twitter data for recognizing customer sentiments about fashion brands and to analyze their overall perception towards the brands. Two brands, Zara and Levis, are considered and users’ tweets related to these brands are analyzed using text mining and Naïve Bayes classifier. The results from this study suggest that social media such as Twitter can serve to be the repository of consumer sentiments and opinions. Sentiment analysis of the tweets can indicate fashion trend and thereby enable fashion brand companies to quickly respond to the ever changing consumer demands.