A very unique porblem for patent classs recommendation system build from scratch using supervised learning and deep learing algorithms

A Service in which allows the user to get the most similar technical words related to their query.

A Custom trained model and hypertuned a pretrained SOTA model based on transformers architecture for comparing the textual similaity between two patent documents.

This study used interpretable classification models to identify patterns of terrorist attacks, according to known characteristics derived from historical data. A For this purpose, we used the Global Terrorism Database (GTD) , which is an open-source database on terrorist attacks around the world from 1970 to 2016. It contains data on more than 170,000 domestic and international terrorist incidents, including dozens of features on location, tactics, perpetrators, targets, and outcomes of the events.

The dataset consists of training data, validation data, and testing data. The training data consists of 5,216 chest x-ray images with 3,875 images shown to have pneumonia and 1,341 images shown to be normal. The validation data is relatively small with only 16 images with 8 cases of pneumonia and 8 normal cases.

• Complete deployment of the iris, breast cancer, and wine quality dataset for visualization using the KNN, SVM, and random forest algorithms from Machine Learning using STREAMLIT. In this application, you can compare the accuracy of the above three algorithms on the same dataset and can decide which is best and you can somewhat calculate the parameters also to see the change in accuracy while the parameters are changed.

In any text document, there are particular terms that represent specific entities that are more informative and have a unique context. These entities are known as named entities , which more specifically refer to terms that represent real-world objects like people, places, organizations, and so on, which are often denoted by proper names. A naive approach could be to find these by looking at the noun phrases in text documents. Named entity recognition (NER) , also known as entity chunking/extraction , is a popular technique used in information extraction to identify and segment the named entities and classify or categorize them under various predefined classes.

With our busy schedule, we prefer to read the summary of those articles before we decide to jump in for reading the entire article. Reading a summary helps us to identify the interest area, gives a brief context of the story. Summarization can be defined as the task of producing a concise and fluent summary while preserving key information and overall meaning.

Dataset was analyzed using Word2Vec algorithm, KMeans clustering, and tfidf weighting. Based on word embeddings trained for given dataset using gensim’s Word2Vec. Main steps included detection of negative and positive clusters in word vectors space with use of sklearn’s implementation of KMeans clustering algorithm, which were then used to transform every sentence into vector of replaced sentiment scores for a given words in a sentence. Second vector for given sentence was obtained through replacing all words in a sentence with their corresponding tfidf-scores. Final prediction was obtained as a dot product from these two vectors for each sentence - if their dot product was positive, the overall sentiment was predicted as positive, and if dot product was negative, overall sentiment was predicted as negative.

• Script to automatically buy/sell Options and Stocks at a predefined profit/loss. • Using different stock market studies and strategies predicting the trend and getting a buy/sell signal. • The signal given by the prediction model will be read by the Auto Script and place buy/sell orders.