The telecommunications industry faces a constant challenge in retaining customers amidst fierce competition, making accurate churn prediction a critical aspect of business strategy. In this paper, we propose a novel hybrid model, implemented in Python, that combines Convolutional Neural Networks (CNNs) with Gradient Boosting Machines (GBMs) to enhance customer churn prediction accuracy. Leveraging a comprehensive dataset encompassing demographic details, service usage, payment information, and customer support interactions, our model extracts intricate patterns from the data using CNNs and integrates them with traditional features for robust prediction. Through extensive experimentation and evaluation, we demonstrate that our proposed CNN-GBM model achieves an outstanding accuracy of 99%, surpassing other existing approaches by 2.6%. The model's performance is evaluated using standard metrics such as accuracy, precision, recall, and F1-Score, showcasing its superiority over traditional methods like Random Forest and Support Vector Machine. The CNN-GBM model's remarkable accuracy and superior performance highlight its efficacy in accurately identifying churned customers while minimizing false positives, thus providing a valuable tool for telecom companies to implement targeted retention strategies. Moreover, our methodology offers scalability and generalizability, making it applicable across industries facing similar churn challenges. Overall, our proposed hybrid CNNGBM model presents a significant advancement in customer churn prediction, offering telecom companies a reliable solution to improve customer retention and competitiveness in the market.
Opinion mining, which can be classified as process of extracting subjective information from text data, remains one of the most widely researched areas in NLP even today. Because of its ability to gauge thoughts and opinions of people it has garnered lot of interest from both scholars and practitioners. A Lot of advancement has been made in this area with the help of large language models (LLMs). This paper aims to compare the sentiment classification on Amazon product review dataset using the various types of LLMs, including BERT and TF-IDF models. Thus, the resultant dataset containing 59,794 totalreviews was pre-processed and further split into the training and testing sets. When performing the Exploratory Data Analysis (EDA) it was determined there were three sentiments; Positive, Negative and Neutral. The measurements, namely F1- score, recall, accuracy, and precision, were used to compare the performances of the developed models. Analysis showed that an accuracy of TF-IDF model was enhanced by 15. 59% as compared to the BERT model that yielded an accuracy of only 78. 91%. This study further embraces the use of TF-IDF and LLM for sentiment analysis and highlights directions for future studies to improve the model reliability and efficiency by eradicating false prediction gaps and integrating other complicated approaches such as ensemble learning.
This research explores a novel hybrid neural network architecture for stock price forecasting that integrates Variational Quantum Layers (VQLs) to enhance efficiency and trainability. It examines various quantum-classical algorithms through extensive simulations on both classical and quantum hardware, utilizing key stock indicators like MACD, EMA, Bollinger Bands, and momentum metrics, alongside sentiment analysis of financial news. The dataset used includes real-time stock prices for 15 companies, focusing on Merck & Co. (MRK). By framing stock price forecasting as a binary classification problem, It proposes QLSTM4FM i.e. a unique framework based on quantum-assisted LSTM model, which significantly enhances stock price forecasting. It conducts a thorough and comprehensive performance evaluation of the proposed framework against classical LSTM models. Results show that QLSTM4FM, featuring quantum-enhanced layers, outperforms classical LSTM models in accuracy, lower loss, and faster convergence, demonstrating the potential of quantum computing in financial forecasting.
Today, agricultural production drives the economy. Agriculture has numerous facets, and plant disease diagnosis is one of the most important. Plant diseases are very common. Disease detection prevents yield and quantity losses. Plant diseases are studied through studying plant patterns. Environmentally friendly farming requires monitoring plant health and leaf diseases. Traditional methods have detected plant leaf diseases for decades. Several research studies have shown that effective methods for plant disease identification are still needed. Thus, deep learning and image processing architectures recognize plant leaf diseases. Image Acquisition, Pre-Processing, Segmentation, Feature Extraction, and Classification comprise this illness detection method. Convolutional Neural Networks (CNN) are also used on input datasets. This method simplifies implementation because the CNN evaluates all discriminant features. CNN was compared to other classifiers in a comprehensive analysis. Brown spot, grey spot, rust, and other leaf spots can be treated immediately with the proposed work.
Distributed Ledger Technology (DLT) is a decentralized database system where transactions are recorded and verified across multiple nodes. Its key features include immutability, time-stamping, and consensus-based validation. Numerous DLT applications are in supply chain management, intellectual property, cross border payments, energy trading, real estate, and online donations. DeFi, a combination of cryptocurrency and blockchain technology, offers financial services without intermediaries. Hence transactions with various digital assets based on cryptocurrency price feeds needs an automated framework. Smart contracts, self-executing contracts with terms directly written into code, automate processes and reduce manual intervention. This paper proposes a decentralized financial trading model using the AAVE protocol. AAVE is a decentralized platform that allows for transactions with various digital assets based on cryptocurrency price feeds. Proposed model uses Chainlink, a decentralized oracle network, to provide accurate and reliable price feeds. IPFS is used for data storage, while Graph is employed for indexing and querying blockchain data. The paper presents an example of a DeFi protocol to simulate banking operations, showcasing the potential of DeFi and DLT in revolutionizing traditional banking processes.
Water supply systems through motor-pump set are required in many places including domestic, industries and agriculture. Power consume by utility grid to drive the motors is more burden and demand high reactive power due to normally using induction motors to drive water pump. Hence, powered by Photovoltaic system (PVS) based induction motor driven standalone water supply systems are providing solution for many issues including over load in grid, pollution, etc. in general, battery storage units are highly recommended for PVS based standalone power supply units. However, cost will be increased by using batteries due to regular maintenance, capital cost, replacements, safety and size etc. In fact, no need of storing power in the case of water pumping applications, instead of using batteries, the energy produced by PVS can be utilized directly to pump the water by using proper energy management and control. Hence, battery less water supply system is considered in this paper. To harvest possible maximum energy from PVS during partial shading phenomenon, the incremental conductance (IC) algorithm is combined with a MIWO: Modified invasive weed optimization technique. The IC algorithm, based on MIWO, adjusts the voltage signal reference value according to the solar irradiance on multiple panels in PVS to achieve the operation of Maximum Power Point (MPP). In order to eliminate an extra converter, a single stage system is established by working a five level inverter as a MPPT converter of the PVS. A speed sensorless control is developed on a five level inverter by balancing power between generation and consumption to manage energy management system in this paper. Hardware – in the – Loop is performed on the OPAL-RT platform to test the performance of the developed model.