Financial News Analytics Using Fine-Tuned Llama 2 GPT Model

The paper considers the possibility to fine-tune Llama 2 GPT large language model (LLM) for the multitask analysis of financial news. For fine-tuning, the PEFT/LoRA based approach was used. In the study, the model was fine-tuned for the following tasks: analysing a text from financial market perspectives, highlighting main points of a text, summarizing a text and extracting named entities with appropriate sentiments. The obtained results show that the fine-tuned Llama 2 model can perform a multitask financial news analysis with a specified structure of response, part of response can be a structured text and another part of data can have JSON format for further processing. Extracted sentiments for named entities can be considered as predictive features in supervised machine learning models with quantitative target variables.

Analysis of Disinformation and Fake News Detection Using Fine-Tuned Large Language Model

The paper considers the possibility of fine-tuning Llama 2 large language model (LLM) for the disinformation analysis and fake news detection. For fine-tuning, the PEFT/LoRA based approach was used. In the study, the model was fine-tuned for the following tasks: analysing a text on revealing disinformation and propaganda narratives, fact checking, fake news detection, manipulation analytics, extracting named entities with their sentiments. The obtained results show that the fine-tuned Llama 2 model can perform a deep analysis of texts and reveal complex styles and narratives. Extracted sentiments for named entities can be considered as predictive features in supervised machine learning models.

Analytics of Business Time Series Using Machine Learning and Bayesian Inference

In the survey we consider the case studies on sales time series forecasting, the deep learning approach for forecasting non-stationary time series using time trend correction, dynamic price and supply optimization using Q-learning, Bitcoin price modeling, COVID-19 spread impact on stock market, using social networks signals in analytics. The use of machine learning and Bayesian inference in predictive analytics has been analyzed.

Forecasting of Non-Stationary Sales Time Series Using Deep Learning

The paper describes the deep learning approach for forecasting non-stationary time series with using time trend correction in a neural network model. Along with the layers for predicting sales values, the neural network model includes a subnetwork block for the prediction weight for a time trend term which is added to a predicted sales value. The time trend term is considered as a product of the predicted weight value and normalized time value. The results show that the forecasting accuracy can be essentially improved for non-stationary sales with time trends using the trend correction block in the deep learning model.

Methods of Informational Trends Analytics and Fake News Detection on Twitter

In the paper, different approaches for the analysis of news trends on Twitter has been considered. For the analysis and case study, informational trends on Twitter caused by Russian invasion of Ukraine in 2022 year have been studied. A deep learning approach for fake news detection has been analyzed. The use of the theory of frequent itemsets and association rules, graph theory for news trends analytics have been considered.

Bitcoin Price Predictive Modeling Using Expert Correction

The paper studies the linear model for Bitcoin price which includes regression features based on Bitcoin currency statistics, mining processes, Google search trends, Wikipedia pages visits. The pattern of deviation of regression model prediction from real prices is simpler comparing to price time series. It is assumed that this pattern can be predicted by an experienced expert. In such a way, using the combination of the regression model and expert correction, one can receive better results than with either regression model or expert opinion only. It is shown that Bayesian approach makes it possible to utilize the probabilistic approach using distributions with fat tails and take into account the outliers in Bitcoin price time series.

Sales Time Series Analytics Using Deep Q-Learning

The article describes the use of deep Q-learning models in the problems of sales time series analytics. In contrast to supervised machine learning which is a kind of passive learning using historical data, Q-learning is a kind of active learning with goal to maximize a reward by optimal sequence of actions. Model free Q-learning approach for optimal pricing strategies and supply-demand problems was considered in the work. The main idea of the study is to show that using deep Q-learning approach in time series analytics, the sequence of actions can be optimized by maximizing the reward function when the environment for learning agent interaction can be modeled using the parametric model and in the case of using the model which is based on the historical data. In the pricing optimizing case study environment was modeled using sales dependence on extras price and randomly simulated demand. In the pricing optimizing case study, the environment was modeled using sales dependence on extra price and randomly simulated demand. In the supply-demand case study, it was proposed to use historical demand time series for environment modeling, agent states were represented by promo actions, previous demand values and weekly seasonality features. Obtained results show that using deep Q-learning, we can optimize the decision making process for price optimization and supply-demand problems. Environment modeling using parametric models and historical data can be used for the cold start of learning agent. On the next steps, after the cold start, the trained agent can be used in real business environment.

Forming Predictive Features of Tweets for Decision-Making Support

The article describes the approaches for forming different predictive features of tweet data sets and using them in the predictive analysis for decision-making support. The graph theory as well as frequent itemsets and association rules theory is used for forming and retrieving different features from these datasests. The use of these approaches makes it possible to reveal a semantic structure in tweets related to a specified entity. It is shown that quantitative characteristics of semantic frequent itemsets can be used in predictive regression models with specified target variables.

Bayesian Regression Approach for Building and Stacking Predictive Models in Time Series Analytics

The paper describes the use of Bayesian regression for building time series models and stacking different predictive models for time series. Using Bayesian regression for time series modeling with nonlinear trend was analyzed. This approach makes it possible to estimate an uncertainty of time series prediction and calculate value at risk characteristics. A hierarchical model for time series using Bayesian regression has been considered. In this approach, one set of parameters is the same for all data samples, other parameters can be different for different groups of data samples. Such an approach allows using this model in the case of short historical data for specified time series, e.g. in the case of new stores or new products in the sales prediction problem. In the study of predictive models stacking, the models ARIMA, Neural Network, Random Forest, Extra Tree were used for the prediction on the first level of model ensemble. On the second level, time series predictions of these models on the validation set were used for stacking by Bayesian regression. This approach gives distributions for regression coefficients of these models. It makes it possible to estimate the uncertainty contributed by each model to stacking result. The information about these distributions allows us to select an optimal set of stacking models, taking into account the domain knowledge. The probabilistic approach for stacking predictive models allows us to make risk assessment for the predictions that are important in a decision-making process.