As a company, proper financial planning is challenging. The knowledge is specific and competent experts are scarce. Poor financial management has a high cost. It results in penalty fees, missed opportunities, and return on investment. CAUSALYSIS empowers small and medium businesses with financial scenario planning powered by Causal Machine Learning. We describe a use case for causal machine learning on the ROI of property rentals.

Machine learning models using transaction records as inputs are popular among financial institutions. The most efficient models use deep-learning architectures similar to those in the NLP community, posing a challenge due to their tremendous number of parameters and limited robustness. In particular, deep-learning models are vulnerable to adversarial attacks: a little change in the input harms the model's output. In this work, we examine adversarial attacks on transaction records data and defenses from these attacks. The transaction records data have a different structure than the canonical NLP or time-series data, as neighboring records are less connected than words in sentences, and each record consists of both discrete merchant code and continuous transaction amount. We consider a black-box attack scenario, where the attack doesn't know the true decision model and pay special attention to adding transaction tokens to the end of a sequence. These limitations provide a more realistic scenario, previously unexplored in the NLP world. The proposed adversarial attacks and the respective defenses demonstrate remarkable performance using relevant datasets from the financial industry. Our results show that a couple of generated transactions are sufficient to fool a deep-learning model. Further, we improve model robustness via adversarial training or separate adversarial examples detection. This work shows that embedding protection from adversarial attacks improves model robustness, allowing a wider adoption of deep models for transaction records in banking and finance.

Recommender systems have become an essential instrument in a wide range of industries to personalize the user experience. A significant issue that has captured both researchers' and industry experts' attention is the cold start problem for new items. This work presents a graph neural network recommender system using item hierarchy graphs and a bespoke architecture to handle the cold start case for items. The experimental study on multiple datasets and millions of users and interactions indicates that our method achieves better forecasting quality than the state-of-the-art with a comparable computational time.

Time series prediction aims to predict future values to help stakeholders make proper strategic decisions. This problem is relevant in all industries and areas, ranging from financial data to demand to forecast. However, it remains challenging for practitioners to select the appropriate model to use for forecasting tasks. With this in mind, we present a model architecture based on Graph Neural Networks to provide model recommendations for time series forecasting. We validate our approach on three relevant datasets and compare it against more than sixteen techniques. Our study shows that the proposed method performs better than target baselines and state of the art, including meta-learning. The results show the relevancy and suitability of GNN as methods for model recommendations in time series forecasting.

Topological Data Analysis (TDA) is a recent approach to analyze data sets from the perspective of their topological structure. Its use for time series data has been limited. In this work, a system developed for a leading provider of cloud computing combining both user segmentation and demand forecasting is presented. It consists of a TDA-based clustering method for time series inspired by a popular managerial framework for customer segmentation and extended to the case of clusterwise regression using matrix factorization methods to forecast demand. Increasing customer loyalty and producing accurate forecasts remain active topics of discussion both for researchers and managers. Using a public and a novel proprietary data set of commercial data, this research shows that the proposed system enables analysts to both cluster their user base and plan demand at a granular level with significantly higher accuracy than a state of the art baseline. This work thus seeks to introduce TDA-based clustering of time series and clusterwise regression with matrix factorization methods as viable tools for the practitioner.

Demand forecasting of hierarchical components is essential in manufacturing. However, its discussion in the machine-learning literature has been limited, and judgemental forecasts remain pervasive in the industry. Demand planners require easy-to-understand tools capable of delivering state-of-the-art results. This work presents an industry case of demand forecasting at one of the largest manufacturers of electronics in the world. It seeks to support practitioners with five contributions: (1) A benchmark of fourteen demand forecast methods applied to a relevant data set, (2) A data transformation technique yielding comparable results with state of the art, (3) An alternative to ARIMA based on matrix factorization, (4) A model selection technique based on topological data analysis for time series and (5) A novel data set. Organizations seeking to up-skill existing personnel and increase forecast accuracy will find value in this work.