Machine Learning and Predictive Analytics in Accounting, Finance, and Management

Permanent URI for this collection


Recent Submissions

Now showing 1 - 4 of 4
  • Item
    Transformer-based Summarization and Sentiment Analysis of SEC 10-K Annual Reports for Company Performance Prediction
    ( 2022-01-04) Hsieh , Hsin-Ting ; Hristova, Diana
    Annual reports published by companies contain important insights regarding their performance and are often analyzed in a manual, subjective manner. We address this point by combining the streams of research on text summarization and topic modelling with the one on sentiment analysis. Our approach consists of the steps of text summarization using BERTSUMEXT, topic modelling with LDA, sentiment analysis with FinBERT, and performance prediction with Decision Trees and Random Forest. The result provides decision makers with an interpretable and condensed representation of the content of annual reports, together with its relationship to future company performance. We evaluate our approach on 10-K reports, demonstrating both its interpretability for analysts and explanatory power regarding future company performance.
  • Item
    A Novel Deep Learning Model For Hotel Demand and Revenue Prediction amid COVID-19
    ( 2022-01-04) Farhangi, Ashkan ; Huang, Arthur ; Guo, Zhishan
    The COVID-19 pandemic has cast a substantial impact on the tourism and hospitality sector. Public policies such as travel restrictions and stay-at-home orders had significantly affected tourist activities and service businesses' operations and profitability. It is essential to develop interpretable forecasting models to support managerial and organizational decision-making. We developed DemandNet, a novel deep learning framework for predicting time series data under the influence of the COVID-19 pandemic. The DemandNet framework has the following unique characteristics. First, it selects the top static and dynamic features embedded in the time series data. Second, it includes a nonlinear model which can provide interpretable insight into the previously seen data. Third, a novel prediction model is developed to leverage the above characteristics to make robust long-term forecasts. We evaluated DemandNet using daily hotel demand and revenue data from eight cities in the US between 2013 and 2020. Our findings reveal that DemandNet outperforms the state-of-art models and can accurately predict the effect of the COVID-19 pandemic on hotel demand and revenue.
  • Item
    Analysis of a Debt Collection Process Using Bayesian Networks
    ( 2022-01-04) Koehler, Benedikt ; Fromm, Hansjoerg
    Many companies rely on professional debt-collection agencies to handle their outstanding debts. These agencies conduct a debt collection process consisting of successive, escalating actions with the aim of getting a debtor to settle an overdue claim. The sequence of actions is administered by agents who often have to make decisions on a case-by-case basis. This requires understanding of complex data and making decisions under uncertainty. This decision-making process has hardly been investigated so far. We are proposing Bayesian networks as the analytical basis for a decision support system. Bayesian networks are strong in dealing with uncertainties. They can be used for both predicting the success of a case and making recommendations on actions. The evaluation shows that Bayesian networks have a very good predictive performance which gets even better as the process evolves. With this instrument, the agents can make better-informed decisions in the debt collection process.
  • Item