Machine Learning Approaches to Top Quark Flavor-Changing Four-Fermion Interactions in Trilepton Signals at the LHC

We explore the top quark flavor-changing 4-Fermi interactions ($tuee$ and $tcee$) with scalar, vector, and tensor structures using machine learning models to analyze tri-lepton processes at the LHC. The study is performed using $t\bar{t}$ and $tW$ processes, where a top quark decays into $u/c+e^{+}+e^{-}$. The analysis incorporates both reducible and irreducible backgrounds while accounting for realistic detector effects. The dominant backgrounds for these trilepton signatures arise from $t\bar{t}$ production, single top quark production in association with $V$, and $VV$ production (where $V = W, Z$). These backgrounds are significantly reduced using machine learning-based classification models, which optimize event selection and improve signal sensitivity. For an integrated luminosity of 3000 fb$^{-1}$ at the LHC, we find that the expected $95\%$ confidence level (CL) limits on the scale of 4-Fermi FCNC interactions reach $\Lambda \leq 5.5$ TeV for $tuee$ and $\Lambda \leq 5.7$ TeV for $tcee$ in the $t\bar{t}$ channel, and $\Lambda \leq 1.9$ TeV ($tuee$) and $\Lambda \leq 2.0$ TeV ($tcee$) in the $tW$ channel. We also provide an interpretation of our EFT analysis in the context of a specific $Z'$ model, illustrating how the derived constraints translate into bounds on the parameter space of a heavy neutral gauge boson mediating flavor-changing interactions.